Search

The fundamental objective of a modern power system lies in ensuring reliable and effective energy access for its customers. The assessment and determination of optimal operating conditions for power systems involve the utilization of the optimal power flow (OPF) tool. By considering critical factors such as generator power, bus voltages, and line power flow limits while satisfying the power balance equations, the OPF tool enables the identification of the most favorable configuration for efficient power system operation. Traditional optimization methods have limitations in addressing complex power system problems due to poor convergence and long computational times. As a result, computational intelligence tools have gained popularity in recent years. These tools are versatile and enable efficient solution of power system problems by effectively handling qualitative constraints. This paper presents a well-organized and comprehensive review of the algorithms used in power system optimization in the existing literature, encompassing the most recent developments in the field. Specifically, it examines the application of various population-based artificial intelligence techniques that have gained widespread adoption over the past decade (2012–2022). The aim of these techniques is to resolve an OPF problem. This paper organizes the reviewed papers into various types of population-based metaheuristic algorithms, each one implemented sequentially to deal with the OPF problem in the same chronological order in which they appeared in the literature. [ABSTRACT FROM AUTHOR]

Detecting tumors using gene analysis in microarray data is a critical area of research in artificial intelligence and bioinformatics. However, due to the large number of genes compared to observations, feature selection is a central process in microarray analysis. While various gene selection methods have been developed to select the most relevant genes, these methods' efficiency and reliability can be improved. This paper proposes a new two-phase gene selection method that combines the ReliefF filter method with a novel version of the spider wasp optimizer (SWO) called RSWO-MPA. In the first phase, the ReliefF filter method is utilized to reduce the number of genes to a reasonable number. In the second phase, RSWO-MPA applies a recursive spider wasp optimizer guided by the marine predators algorithm (MPA) to select the most informative genes from the previously selected ones. The MPA is used in the initialization step of recursive SWO to narrow down the search space to the most relevant and accurate genes. The proposed RSWO-MPA has been implemented and validated through extensive experimentation using eight microarray gene expression datasets. The enhanced RSWO-MPA is compared with seven widely used and recently developed meta-heuristic algorithms, including Kepler optimization algorithm (KOA), marine predators algorithm (MPA), social ski-driver optimization (SSD), whale optimization algorithm (WOA), Harris hawks optimization (HHO), artificial bee colony (ABC) algorithm, and original SWO. The experimental results demonstrate that the developed method yields the highest accuracy, selects fewer features, and exhibits more stability than other compared algorithms and cutting-edge methods for all the datasets used. Specifically, it achieved an accuracy of 100.00%, 94.51%, 98.13%, 95.63%, 100.00%, 100.00%, 92.97%, and 100.00% for Yeoh, West, Chiaretti, Burcyznski, leukemia, ovarian cancer, central nervous system, and SRBCT datasets, respectively. [ABSTRACT FROM AUTHOR]

Data mining and machine learning require feature selection because features can dramatically improve model performance. In contrast, there are no polynomial solutions for selecting a subset feature. It is possible to achieve this by using meta-heuristic algorithms, specifically population-based algorithms that are able to provide a subset of features that is optimal and not exact. Meta-heuristic algorithms face challenges such as staying in local minima, easily falling into local optimum, weakly global searchability, premature convergence, and slow convergence speeds. However, recent research has limitations such as high complexity and weak initialization. In order to overcome these limitations, a three-stage model is proposed. In the first stage, the correlation of features and the correlation of features with class are considered during feature selection and used to create the initial population in the pathfinder optimization algorithm (PFA). PFA is a population-based algorithm and has some drawbacks, in the last iterations, the fluctuation rate (A) and vibration vector (ε) parameters converge to 0, and finding a new solution is impossible. As a second stage, a fuzzy inference system is designed to adjust these parameters adaptively and is called fuzzy-pathfinder optimization (FPO). In the third stage, FPO is used to select relevant features based on classification error, proportion of selected features, and redundancy. Finally, different algorithms such as simulated annealing (SA), differential evolutionary (DE), genetic algorithm (GA), particle swarm optimization (PSO), PFA, estimation of distribution algorithm (EDA), and symmetrical uncertainty criterion (SUC-PSO) are used for comparison. Based on the results, the proposed model is able to reach an average accuracy of 96% on average. Based on a comparison of the proposed algorithm with SA, DE, GA, PSO, PFA, EDA, and SUC-PSO, the objective function is improved by 17.3%, 5.6%, 3.0%, 4.5%, 5.0%, 0.5%, and 1.2%, respectively. The use of comprehensive objective functions, the adaptive adjustment of parameters, and the creation of a targeted initial population are key strengths of FPO. [ABSTRACT FROM AUTHOR]

This paper proposes a novel social cognitive learning-based metaheuristic called kids Learning Optimizer (KLO), inspired by the early social learning behavior of kids organized as families in societal setup. In a society, people are organized as family groups (parents and children) where they interact with each other within and outside their family. This interaction plays a vital role in early brain development, mannerisms, and behavioral learning. Early childhood learning is affected by various stimuli in their surroundings at different stages of life (newborn, infant, toddler, pre-school). This idea motivated us to map the decentralized learning concept of families and their interactions into a new algorithm where search agents (individuals) are arranged/organized in families, and they interact with each other at different stages of life to find the optimal solution. The algorithm is tested against 116 challenging benchmark functions including 31 unimodal, 63 multimodal, 14 CEC'2017 functions, and eight constrained functions. The algorithm is compared with 10 state-of-the-art algorithms. Friedman's Mean Rank (FMR) and Wilcoxon rank-sum test (WRS) are used to measure the performance of competing algorithms. In the first two experiments, unimodal and multimodal benchmark functions are used to measure the explorative and exploitative ability of the algorithm. FMR and WRS show KLO outperformed all other algorithms. In the third experiment, the proposed method is tested against 14 CEC'2017 functions and eight constrained functions along with three real life mechanical engineering optimization problems. KLO proved to be better or equivalent to other competing algorithms. [ABSTRACT FROM AUTHOR]

This paper proposes a novel hybrid metaheuristic algorithm called the remora crayfish optimization algorithm (HRCOA) designed for solving continuous optimization problems. The crayfish optimization algorithm (COA), recently proposed as a meta-heuristic algorithm (MA), exhibits certain limitations such as imbalanced exploration and exploitation capacities, susceptibility to premature optimization, and a propensity for stagnation. To address these shortcomings, we incorporate the exploitation operators from the remora optimization algorithm (ROA) to enhance the exploitative behaviors of COA. In addition, we simplify the summer resort operator in the original COA to streamline the search operator design, thus avoiding unnecessary complexity. Furthermore, numerical experiments on 10-dimensional (D) and 20-D CEC2022 benchmark functions, 50-D and 100-D CEC2020 benchmark functions, engineering optimization problems, and wireless sensor networks (WSNs) coverage optimization problems are conducted to investigate the performance of our proposed HRCOA comprehensively. We compare the proposed HRCOA against eight well-known state-of-the-art MAs, including CMAES and the original COA, as competitor algorithms. The experimental and statistical results confirm the effectiveness, competitiveness, and scalability of our proposal. Finally, we conclude that the proposed HRCOA possesses significant potential for addressing diverse optimization challenges in real-world scenarios. [ABSTRACT FROM AUTHOR]

Software defect prediction is a critical challenge within software engineering aimed at enhancing software quality by proactively identifying potential defects. This approach involves selecting defect-prone modules ahead of the testing phase, thereby reducing testing time and costs. Machine learning methods provide developers with valuable models for categorising faulty software modules. However, the challenge arises from the numerous elements present in the training dataset, which frequently reduce the accuracy and precision of classification. Addressing this, selecting effective features for classification from the dataset becomes an NP-hard problem, often tackled using metaheuristic algorithms. This study introduces a novel approach, the Binary Chaos-based Olympiad Optimisation Algorithm, specifically designed to select the most impactful features from the training dataset. By selecting these influential features for classification, the precision and accuracy of software module classifiers can be notably improved. The study's primary contributions involve devising a binary variant of the chaos-based Olympiad optimisation algorithm to meticulously select effective features and construct an efficient classification model for identifying faulty software modules. Five real-world and standard datasets were utilised across both the training and testing phases of the classifier to evaluate the proposed method's effectiveness. The findings highlight that among the 21 features within the training datasets, specific metrics such as basic complexity, the sum of operators and operands, lines of code, quantity of lines containing code and comments, and the sum of operands have the most significant influence on software defect prediction. This research underscores the combined effectiveness of the proposed method and machine learning algorithms, significantly boosting accuracy (91.13%), precision (92.74%), recall (97.61%), and F1 score (94.26%) in software defect prediction. [ABSTRACT FROM AUTHOR]

Meta-heuristic algorithms, due to their high search speed and strong generalization ability, are frequently applied in programs mainly to discover the corresponding optimal strategy for any problem in view of their defined rules. After years of collision evolution, they have been continuously used to solve the complex, unordered and diverse optimization problems and improve efficiency. Aiming at the problems of low convergence accuracy and easy to fall into local optima of the traditional Harris hawks optimization algorithm, a compound improved Harris Hawks Optimization algorithm (CIHHO) is proposed. Firstly, the early circling exploration and later attack exploitation phase of the dynamic adjustment algorithm for environmental factors is introduced to regulate the energy of Harris hawks; Secondly, the concept of Versoria function is introduced to modify the random jump strength and raise the data grabbing ability of local space; Introducing the Levy flight function to adjust the factor and reduce the disturbance impact of Levy flight is beneficial for getting rid of the local space after entering the exploitation phase, and introducing random white noise to reduce step size and improve algorithm accuracy. Taking CEC 2017 test function suite set as the core, the performance of CIHHO algorithm is analyzed. Firstly, the performance of CIHHO algorithm is compared with HHO, HHO_JOS, LHHO, LMHHO and NCHHO. Secondly, the performance of unimodal function, multimodal function, mixed function and compound function is compared with other 7 improved algorithms. Finally, ablation experiments are carried out. The convergence value of the iterative curve obtained is more quantitative than the improved algorithm, The generality of the improved CIHHO algorithm in solving multiple optimization problems with different dimensions is verified. Further applying the CIHHO algorithm to three different engineering experiments, the minimum cost calculation results directly demonstrate that the CIHHO algorithm obtained has certain advantages in dealing with search space problems. [ABSTRACT FROM AUTHOR]

Introducing a novel meta-heuristic optimization algorithm, the Flood Algorithm (FLA) draws inspiration from the intricate movement and flow patterns of water masses during flooding events in river basins. FLA mathematically models key phenomena such as the movement of water toward slopes, flow rates over time, soil permeability effects, and periodic increases and decreases in water levels from precipitation and losses. Leveraging these models, the algorithm guides the movement and evolution of a population of potential solutions toward enhanced optimality. The algorithm endeavors to establish an appropriate correlation between the fundamental aspects of natural flood events and the optimization process. Its formulation and working mechanism are described in detail. It operates in two main phases—a regular movement phase, where the population moves naturally toward current best solutions, and a flooding phase, which introduces random disturbances to increase diversity. New solutions are periodically introduced while weaker ones are removed, mirroring the natural cycles of water levels. FLA's effectiveness is demonstrated through its application on well-known benchmark optimization problems and engineering design problems. Extensive comparisons have been carried out on CEC2005 functions using 16 algorithms in both basic and enhanced modes, as well as on CEC2014 functions with dimensions 30, 50, and 100 using a total of 20 other algorithms. These rigorous studies unequivocally confirm the robustness and strength of the proposed algorithm. Furthermore, the algorithm's performance on 12 constrained engineering problems demonstrates its ability to tackle real-world challenges. The FLA's source code is publicly available at https://www.optim-app.com/projects/fla. [ABSTRACT FROM AUTHOR]

Rockburst is one of the most hazardous geological disasters in underground engineering due to its complex causes and destructive nature. To address this, there is an imperative for methodologies that can predict rockbursts quickly and effectively to mitigate preemptively the risks and damages. In this study, 259 rockburst instances were analyzed, employing six rockburst feature parameters: maximum tangential stress (σθ), uniaxial compressive strength of rock (σc), uniaxial tensile strength of rock (σt), stress coefficient (σθ/σt), rock brittleness coefficient (σc/σt), and elastic energy index (Wet) as inputs. By integrating three novel meta-heuristic algorithms—dingo optimization algorithm (DOA), osprey optimization algorithm (OOA), and rime-ice optimization algorithm (RIME)—with support vector machine (SVM), hybrid models for long-term rockburst trend prediction were constructed. Performance evaluations through fivefold cross-validation revealed that for the no rockbursts, DOA–SVM (Pop = 200) demonstrated superior predictive performance, achieving an accuracy of 0.9808, precision of 0.9231, recall of 1, and an F1-score of 0.96. For moderate rockbursts, OOA–SVM (Pop = 100) emerged as the most effective, registering an accuracy of 0.9808, precision of 0.9545, recall of 1, and an F1-score of 0.9767. For light and severe rockbursts, DOA–SVM, OOA–SVM, and RIME–SVM showcased comparable predictive outcomes. However, these hybrid models outperformed traditional SVM models optimized with conventional algorithms in terms of accuracy across all rockburst hazard levels. Moreover, the hybrid models underwent additional validation with a new dataset of 20 rockburst instances collected globally, confirming their robust efficacy and exceptional generalization capabilities. An ensuing analysis using local interpretable model-agnostic explanations (LIME) on the six key feature parameters revealed a significant positive correlation between σθ and Wet with the severity of rockbursts. These results not only affirm the superior optimization performance of the DOA, OOA, and RIME algorithms but also their substantial potential to enhance the predictive accuracy of machine learning models in forecasting long-term rockbursts. [ABSTRACT FROM AUTHOR]

The bitterling fish is a prime example of intelligent behavior in nature for survival. The bitterling fish uses the oyster spawning strategy as their babysitter. The female bitterling fish looks for a male fish stronger than other fish to find the right pair. In order to solve optimization issues, the Bitterling Fish Optimization (BFO) algorithm is modeled in this manuscript based on the mating behavior of these fish. The bitterling fish optimization algorithm is more accurate than the gray wolf optimization algorithm, whale optimization algorithm, butterfly optimization algorithm, Harris Hawks optimization algorithm, and black widow optimization algorithm, according to experiments and implementations on various benchmark functions. Data mining and machine learning are two areas where meta-heuristic techniques are frequently used. In trials, the MLP artificial neural network and a binary version of the BFO algorithm are used to lower the detection error for intrusion traffic. The proposed method's accuracy, precision, and sensitivity index for detecting network intrusion are 99.14%, 98.87%, and 98.85%, respectively, according to experiments on the NSL KDD data set. Compared to machine learning approaches like NNIA, DT, RF, XGBoot, and CNN, the proposed method is more accurate at detecting intrusion. The BFO algorithm is used for feature selection in the UNSW-NB15 dataset, and the tests showed that the accuracy of the proposed method is 96.72% in this dataset. The proposed method of the BFO algorithm is also used to improve Kmeans clustering, and the tests performed on the dataset of covid 19, diabetes, and kidney disease show that the proposed method performs better than iECA*, ECA*, GENCLUST + + (G + +) methods. Deep has KNN, LVQ, SVM, ANN, and KNN. [ABSTRACT FROM AUTHOR]

When contemplating the improvement of overall performance in machine learning (ML) models, a critical strategy for optimizing data preparation is feature selection (FS). There has been a significant rise in the popularity of metaheuristic FS algorithms in recent times. This can be attributed to their proficiency in accurately identifying and selecting the most relevant features for ML tasks. This study presents three feature selection strategies that utilize metaheuristic algorithms. The methodologies mentioned include the Gravitational Search Optimization Algorithm (GSA), Emperor Penguin Optimization (EPO), and a hybrid approach of GSA and EPO referred to as hGSAEPO. Previous research has explored the use of baseline algorithms for feature selection in various ML tasks. However, there is a lack of investigation regarding their application specifically in breast cancer(BC) classification. A combination of these two has been utilized for the first occasion. The purpose of selecting BC as the study of investigation is due to the reason that this illness is recognized as the second most prevalent cause of mortality in the female population. If the condition is detected in its initial phases, it can be remedied and can assist individuals in evading superfluous medical processes. The procedure of selecting relevant features holds significant importance in the purpose of predicting ailments like BC. The current research presents an innovative methodology that employs three soft-computing algorithms, EPO, GSA, and their proposed hybrid hGSAEPO to efficiently identify significant features while concurrently decreasing the occurrence of irrelevant ones, simplifying overall complexity and enhancing the accuracy. The utilization of these soft computing methodologies and six ML classifiers presents a viable framework for prognostic research through the classification of data instances on Wisconsin Diagnostic Breast Cancer (WDBC). The experimental findings of eight experiments conducted suggest that the suggested approach exhibits exceptional performance in the context of binary classification for BC by computing astounding results like precision of 0.9800, sensitivity of 0.9700, specificity of 0.9887, F1-score of 0.9539, area under the curve(AUC) surpassing 0.998, with an accuracy of 98.31%. We achieved our objectives by presenting a dependable clinical prediction system for healthcare professionals for efficient diagnosis. [ABSTRACT FROM AUTHOR]

It is very tiresome for a practiser to detect the best feasible sizing design of structural members including reinforced concrete columns that is a highly nonlinear and complicated structural engineering optimization problem. This is due to such a design is practically conducted via conventional trial-and-error computing methods in which resistance to external loads, cost efficiency, and aesthetic factors, etc. have to be considered. This study focuses on minimizing the design cost of primarily proposed reinforced concrete column design problem via three overnew swarm-based optimizers such as Coati Optimization Algorithm, Fox Optimizer and Pelican Optimization Algorithm (POA) that are firstly utilized for this purpose. In this regard, the type of steel rebar distribution, the characteristic strength of the concrete, the height and width of the column section, and the number and diameter of the rebars are treated as discrete design variables of the newly proposed complex reinforced concrete column design cost optimization problem. In solution, the design requirements specified in practice code provisions should also be met. Here, Turkish Building Earthquake Code 2018 specifications are considered as practice structural design constraints. Consequently, the algorithmic performances of three overnew swarm-based metaheuristic optimization algorithms are compared and evaluated in detail. Amongst them, the POA shows most fruitful algorithmic design solution performance. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) system performance and reliability can be improved through the detection of defects in PV modules and the evaluation of their effects on system operation. In this paper, a novel system is proposed to detect and classify defects based on electroluminescence (EL) images. This system is called Fault Detection and Classification (FDC) and splits into four modules, which are (1) Image Preprocessing Module (IPM), (2) Feature Extraction Module (FEM), (3) Feature Selection Module (FSM), and (4) Classification Module (CM). In the first module (i.e., IPM), the EL images are preprocessed to enhance the quality of the images. Next, the two types of features in these images are extracted and fused together through FEM. Then, during FSM, the most important and informative features are extracted from these features using a new feature selection methodology, namely, Feature Selection-based Chaotic Map (FS-CM). FS-CM consists of two stages: filter stage using chi-square to initially select the most effective features and a modified selection stage using an enhanced version of Butterfly Optimization Algorithm (BOA). In fact, BOA is a popular swarm-based metaheuristic optimization algorithm that has only recently found success. While BOA has many benefits, it also has some drawbacks, including a smaller population and an increased likelihood of getting stuck in a local optimum. In this paper, a new methodology is proposed to improve the performance of BOA, called chaotic-based butterfly optimization algorithm. Finally, these selected features are used to feed the proposed classification model through CM. During CM, Hybrid Classification Model (HCM) is proposed. HCM consists of two stages, which are binary classification stage using Naïve Bayes (NB) and multi-class classification stage using enhanced multi-layer perceptron. According to the experimental results, the proposed system FDC outperforms the most recent methods. FDC introduced 98.2%, 89.23%, 87.2%, 87.9%, 87.55%, and 88.20% in terms of accuracy, precision, sensitivity, specificity, g-mean, and f-measure in the same order. [ABSTRACT FROM AUTHOR]

High utility itemset mining is an essential new task in data mining, which is obtained from the extension of frequent itemset mining problems. The difference between these two groups is that in high utility itemset mining, the utilities of the items are essential in addition to the number of items. To find the itemsets with more utilities, defining a minimum utility threshold is necessary by testing different solutions to obtain the desired outcome. This is challenging and needs more time to reach the appropriate value. In this article, we propose a method called TKU-BChOA to explore top-k high utility itemsets according to the number of required itemsets based on the Chimp meta-heuristic algorithm. Because, in comparison with the meta-heuristic methods, the deterministic methods require more time and memory. Experimental results on five datasets show that the proposed approach outperforms the previous deterministic methods in memory usage. The proposed method performs better in terms of time and memory on large datasets than other approximate methods and is more accurate. [ABSTRACT FROM AUTHOR]

The Harris hawk Optimization (HHO) has the advantage of employing various local search strategies to adapt to different situations during the exploitation phase. Hence, HHO can search deeper into discovered prospective regions. The reason of poor robustness is that HHO exhibits high randomness in the exploration phase. In the scene of optimizing high-dimensional or multimodal Tasks, the increased dimensionality and parameter correlation lead to the problem of local optimal regions, which affects the accuracy and convergence of the solution. To address these issues, we propose Dynamic Random Mutation Hybrid Harris hawk Optimization (DRM-HHHO). In the hybrid algorithm, the Kepler Optimization Algorithm (KOA) was enhanced (called EKOA) to replace the exploration phase of HHO to solve the problem of excessive diffusion. At the end of each iteration, the leader's position is perturbed by the Dynamic Random Mutation (DRM) algorithm. The mutation probability is adjusted based on the dimension to suit problems of different scales. We conduct ablation experiment to test the effectiveness of the two improved mechanisms. Testing our method on the CEC2017 and CEC2019 benchmark functions, we find that the significance of mutation probability differences decreases with increasing dimensionality. Compared to other Metaheuristic Algorithms (MAs), such as WOA, TSA, and so on, DRM-HHHO shows superior overall performance, especially in solving high-dimensional problems. Furthermore, we successfully apply DRM-HHHO to optimize the Kernel Extreme Learning Machine (KELM) critical parameters. DRM-HHHO-KELM outperforms four traditional machine learning methods and five MAs-KELM strategies on the Australian Credit and Pima Indian Diabetes datasets. [ABSTRACT FROM AUTHOR]

Traditional deterministic optimization algorithms are difficult to effectively solve many real-world nonlinear, complex, and high-dimensional optimization problems. The metaheuristic optimization algorithm has evolved in recent years into a kind of very popular algorithm due to its gradient-free and random nature. In this paper, a new metaheuristic algorithm, namely the literature research optimization algorithm (LRO), is proposed. In this algorithm, the literature research process is represented as a mathematical model, and new mechanisms are designed to help realize the global exploration and local exploitation. To evaluate the performance of LRO, three sets of test functions including the standard benchmark set, CEC2017, and CEC2019 are applied first, and then, six engineering problems are employed to further verify it. The Friedman test and Wilcoxon rank sum test are also used to statistically compare the proposed LRO algorithm with ten common existing metaheuristics. The results show that the LRO algorithm outperforms the comparison algorithms on most benchmark functions and that it also performs well in practical engineering applications. The LRO algorithm can provide superior solutions to most optimization problems compared to other metaheuristic algorithms and become a promising candidate for many real-life optimization problems. [ABSTRACT FROM AUTHOR]

In wireless rechargeable sensor networks (WRSNs), due to data collection and charging, energy efficiency is a crucial factor because it affects the network's reliability and performance. Wireless energy transfer (WET) and wireless data collection (WDC) using separate vehicles are two promising new methods for improving the energy efficiency of sensors. We combine WET and WDC on a single mobile vehicle (MV) to charge and collect data from the sensors by traversing specified sojourn locations within the WRSNs. The objective of this work is to maximize data collection per unit of energy and reduce the number of inactive sensors. In order to accomplish this, we propose a novel scheme, namely DCPCS, that includes two heuristics and two optimization algorithms. We utilized the circle-covering algorithm to determine sojourn locations based on energy consumption rates and the location of sensors. The ant lion optimization (ALO) algorithm partitions the network into the minimum number of regions, assigns a MV to each region, and ensures balanced total energy consumption among the MVs. The ALO algorithm utilizes the first heuristic algorithm to validate the regions for the MVs. Subsequently, the discrete grey wolf optimization algorithm determines the optimal order of the sojourn locations for data collection and charging by a MV within a region. To accomplish our objectives, we propose a heuristic data collection and partial charging strategy to determine the sojourn times of the MVs at the sojourn locations. We conduct simulations and compare the results of the proposed DCPCS scheme with three existing schemes. The simulation outcomes demonstrate that our proposed scheme outperforms the other schemes in terms of various performance metrics. [ABSTRACT FROM AUTHOR]

Snake optimizer (SO) is an optimization algorithm drawn from the reproductive habits of serpents. It exhibits outstanding effectiveness in solving continuous optimization problems. However, SO may face some performance challenges related to its population diversity and early convergence behavior. In this paper, we address the challenges of SO by introducing the Hybrid snake optimizer algorithm (HSOA). HSOA is a novel approach to optimization that incorporates two new optimization techniques into the SO algorithm. First, it incorporates a new opposition-based learning technique called Oppositional-mutual learning into the initialization stage of the SO algorithm. Second, it integrates dynamic polynomial mutation, which is an intelligent mutation method, into the initialization and optimization stages of the SO algorithm. These integrated approaches aim to increase the population's diversity of SO, while improving its searchability during its optimization stage. In power systems, the economic load dispatch (ELD) is an intricate optimization problem that becomes more challenging when the restrictions of the valve point effect (VPE) are incorporated into it. ELD with VPE is non-convex, lacking smoothness, and exhibiting nonlinearity that considers operational limitations expressed as both equality and inequality constraints to generate electricity. The suggested HSOA algorithm underwent evaluation and was compared with 47 renowned optimization algorithms across five real-world ELD problems with different specifications: generators with different unit capacities, transmission losses, prohibited operation zones, and Ramp Rate restrictions. The experimental results demonstrate that HSOA produces competitive solutions for the five real-world ELD problems. In detail, HSOA achieves the top rank in three cases of ELD problems with a 3-unit generator, and it secures the second and third positions in high-dimensional ELD problems with 40-unit and 80-unit generators, respectively. The statistical tests confirm the reliability and efficiency of HSOA. In addition, the effectiveness of HSOA was evaluated using the single-objective IEEE-CEC 2014 functions and compared to the results of eight popular metaheuristic algorithms. The results demonstrate that HSOA is a competitive optimization algorithm capable of solving the functions of IEEE-CEC 2014. [ABSTRACT FROM AUTHOR]

This study aimed to forecast dam inflows and subsequently predict its capability in producing HEPP using machine learning and evolutionary optimization techniques. Mahabad Dam, located in the northwest of Iran and recognized as one of the nation's key dams, served as a case study. First, artificial neural networks (ANN) and support vector regression (SVR) were employed to predict dam inflows, with optimization of parameters achieved through Harris hawks optimization (HHO), a robust optimization technique. The data of temperature, precipitation, and dam inflow over a 24-year period on a monthly basis, incorporating various lag times, were used to train these machines. Then, HEPP from the dam was predicted using temperature, precipitation, dam inflow, and dam evaporation as input variables. The models were applied to data covering the years 2000 to 2020. The results of the first part indicated both hybrid models (HHO-ANFIS and HHO-SVR) improved the prediction performance compared to the single models. Based on the results of Taylor's diagram and the error evaluation criteria, the HHO-ANFIS hybrid model (RMSE, MAE, and NSE of 3.90, 2.41, and 0.86, respectively) exerted better performance than HHO-SVR (RMSE, MAE, and NSE of 4.39, 2.70, and 0.86, respectively). The results of the second part showed that using the HHO algorithm to optimize single models (RMSE, MAE, and NSE of 0.2, 10, and 0.90, respectively) predicted HEPP better than single models (RMSE, MAE, and NSE of 0.2, 10, and 0.90, respectively). The results of Taylor's diagram also showed that the HHO-ANFIS model exerted better performance. The findings of this study indicated the promising performance of machine learning models optimized by metaheuristic algorithms in the simultaneous prediction of dam inflows and HEPP in multi-purpose dams for better management and allocation of surface water resources. [ABSTRACT FROM AUTHOR]

Economic dispatch is an important issue in the management of power systems and is the current focus of specialists. In this paper, a new metaheuristic optimization algorithm is proposed, named Social Small Group Optimization (SSGO), inspired by the psychosocial processes that occur between members of small groups to solve real-life problems. The starting point of the SSGO algorithm is a philosophical conception similar to that of the social group optimization (SGO) algorithm. The novelty lies in the introduction of the small group concept and the modeling of individuals' evolution based on the social influence between two or more members of the small group. This conceptual framework has been mathematically mapped through a set of heuristics that are used to update the solutions, and the best solutions are retained by employing a greedy selection strategy. SSGO has been applied to solve the economic dispatch problem by considering some practical aspects, such as valve-point loading effects, sources with multiple fuel options, prohibited operating zones, and transmission line losses. The efficiency of the SSGO algorithm was tested on several mathematical functions (unimodal, multimodal, expanded, and composition functions) and on power systems of varying sizes (ranging from 10-units to 1280-units). The SSGO algorithm was compared with SGO and other algorithms belonging to various categories (such as: evolution-based, swarm-based, human behavior-based, hybrid algorithms, etc.), and the results indicated that SSGO outperforms other algorithms applied to solve the economic dispatch problem in terms of quality and stability of the solutions, as well as computation time. [ABSTRACT FROM AUTHOR]

Accurate estimation of reference evapotranspiration (ET0) is a crucial parameter in implementing precise irrigation strategies and managing regional water resources effectively. While various methods have been proposed to obtain accurate ET0, the conventional approach is complex, uneconomical, and unable to contend with the rising variability and unpredictable weather patterns. Meanwhile, the lack of meteorological data limits the accurate estimation of ET0 via empirical models. Considering the recent approach in coupling ML techniques with optimisation algorithms to enhance the accuracy and robustness of ET0 estimation, this study was conducted to explore the performance of optimised hybrid Support Vector Regression (SVR) models integrated with meta-heuristic algorithms for daily ET0 estimation in Malaysia. Four hybrid SVR models, including SVR-Particle Swarm Optimisation (SVR-PSO), SVR-Whale Optimisation Algorithm (SVR-WOA), SVR-Differential Evolution (SVR-DE), and SVR-Covariance Matrix Adaptation Evolution Strategy (SVR-CMAES), were developed and assessed using the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), coefficient of determination (R2), and Global Performance Index (GPI). The accuracy of the hybrid SVR models was then compared against standalone Machine Learning (ML) and empirical models using limited meteorological data. Accordingly, the findings highlighted the superior accuracy of the SVR-PSO model in estimating ET0, followed closely by the SVR-DE and SVR-CMAES models. The outstanding performance of the SVR-PSO model was attributed to the inherent versatility and robustness of PSO, as well as its core social behaviour and swarm intelligence principles that allow for an exhaustive exploration of the solution space, thus enhancing the model's accuracy and reliability. In conclusion, the integration of SVR with the meta-heuristics algorithm represents a significant advancement in ET0 estimation models with enhanced accuracy. The study underlines the critical role of advanced hybrid models in enhancing ET0 prediction accuracy, thereby supporting the implementation of efficient water resource management and strategic planning across Malaysia. [ABSTRACT FROM AUTHOR]

Supply chain efficiency is a major challenge in today's business environment, where efficient resource allocation and coordination of activities are essential for competitive advantage. Traditional efficiency strategies often struggle for resources for the complex and dynamic network. In response, bio-inspired metaheuristic algorithms have emerged as powerful tools to solve these optimization problems. Referring to the random search nature of metaheuristic algorithms and emphasizing that no metaheuristic algorithm is the best optimizer for all optimization applications, the No Free Lunch (NFL) theorem encourages researchers to design newer algorithms to be able to provide more effective solutions to optimization problems. Motivated by the NFL theorem, the innovation and novelty of this paper is in designing a new meta-heuristic algorithm called Bobcat Optimization Algorithm (BOA) that imitates the natural behavior of bobcats in the wild. The basic inspiration of BOA is derived from the hunting strategy of bobcats during the attack towards the prey and the chase process between them. The theory of BOA is stated and then mathematically modeled in two phases (i) exploration based on the simulation of the bobcat's position change while moving towards the prey and (ii) exploitation based on simulating the bobcat's position change during the chase process to catch the prey. The performance of BOA is evaluated in optimization to handle the CEC 2017 test suite for problem dimensions equal to 10, 30, 50, and 100, as well as to address CEC 2020. The optimization results show that BOA has a high ability in exploration, exploitation, and balance them during the search process in order to achieve a suitable solution for optimization problems. The results obtained from BOA are compared with the performance of twelve well-known metaheuristic algorithms. The findings show that BOA has been successful in handling the CEC 2017 test suite in 89.65, 79.31, 93.10, and 89.65% of the functions for the problem dimension equal to 10, 30, 50, and 100, respectively. Also, the findings show that in order to handle the CEC 2020 test suite, BOA has been successful in 100% of the functions of this test suite. The statistical analysis confirms that BOA has a significant statistical superiority in the competition with the compared algorithms. Also, in order to analyze the efficiency of BOA in dealing with real world applications, twenty-two constrained optimization problems from CEC 2011 test suite and four engineering design problems have been selected. The findings show that BOA has been successful in 90.90% of CEC2011 test suite optimization problems and in 100% of engineering design problems. In addition, the efficiency of BOA to handle SCM applications has been challenged to solve ten case studies in the field of sustainable lot size optimization. The findings show that BOA has successfully provided superior performance in 100% of the case studies compared to competitor algorithms. [ABSTRACT FROM AUTHOR]

Many emerging commercial services are based on the sharing or pooling of resources for common use with the aim of reducing costs. Businesses such as delivery-, mobility-, or transport-as-a-service have become standard in many parts of the world, fulfilling on-demand requests for customers in live settings. However, it is known that many of these problems are NP-hard, and therefore both modeling and solving them accurately is a challenge. Here we focus on one such routing problem, the Ride Pooling Problem (RPP), where multiple customers can request on-demand pickups and drop-offs from shared vehicles within a fleet. The combinatorial optimization task is to optimally pool customer requests using the limited set of vehicles, akin to a small-scale flexible bus route. In this work, we propose a quadratic unconstrained binary optimization (QUBO) program and introduce efficient formulation methods for the RPP to be solved using metaheuristics, and specifically emerging quantum optimization algorithms. [ABSTRACT FROM AUTHOR]

Cloud computing has evolved into an indispensable tool for facilitating scientific research due to its ability to efficiently distribute and process workloads in a virtual environment. Scientific tasks that involve complicated task dependencies and user-defined constraints related to quality of service (QoS) and time constraints require the efficient use of cloud resources. Planning these scientific workflow tasks represents an NP-complete problem, prompting researchers to explore various solutions, including conventional planners and evolutionary optimization algorithms. In this study, we present a novel, multistage algorithm specifically designed to schedule scientific workflows in cloud computing contexts. This approach addresses the challenges of efficiently mapping complex workflows onto distributed cloud resources while considering factors like resource heterogeneity, dynamic workloads, and stringent performance requirements. The algorithm uses the whale optimization algorithm (WOA) with a two-phase approach to shorten execution time, minimize financial costs, and effectively maintain load balancing. [ABSTRACT FROM AUTHOR]

This research introduces a new technique to control constrained nonlinear systems, named Lyapunov-based neural network model predictive control using a metaheuristic optimization approach. This controller utilizes a feedforward neural network model as a prediction model and employs the driving training based optimization algorithm to resolve the related constrained optimization problem. The proposed controller relies on the simplicity and accuracy of the feedforward neural network model and the convergence speed of the driving training based optimization algorithm. The closed-loop stability of the developed controller is ensured by including the Lyapunov function as a constraint in the cost function. The efficiency of the suggested controller is illustrated by controlling the angular speed of three-phase squirrel cage induction motor. The reached results are contrasted to those of other methods, specifically the fuzzy logic controller optimized by teaching learning-based optimization algorithm, the optimized PID with particle swarm optimization algorithm, the neural network model predictive controller based on particle swarm optimization algorithm, and the neural network model predictive controller using driving training based optimization algorithm. This comparative study showcase that the suggested controller provides good accuracy, quickness and robustness due to the obtained values of the mean absolute error, mean square error root mean square error, enhancement percentage, and computing time in the different simulation cases, and it can be efficiently utilized to control constrained nonlinear systems with fast dynamics. [ABSTRACT FROM AUTHOR]

The primary objective of a power system is to provide safe and reliable electrical energy to consumers. This objective is achieved by maintaining the stability of the power system, a multifaceted concept that can be divided into three distinct classes. The focus of this study is on one of these classes, voltage stability. A critical component in maintaining voltage stability is the automatic voltage regulator (AVR) system of synchronous generators. In this paper, a novel control method, the sigmoid-based fractional-order PID (SFOPID), is introduced with the aim of improving the dynamic response and the robustness of the AVR system. The dandelion optimizer (DO), a successful optimization algorithm, is used to optimize the parameters of the proposed SFOPID control strategy. The optimization process for the DO-SFOPID control strategy includes a variety of objective functions, including error-based metrics such as integral of absolute error, integral of squared error, integral of time absolute error, and integral of time squared error, in addition to the user-defined Zwee Lee Gaing's metric. The effectiveness of the DO-SFOPID control technique on the AVR system has been rigorously investigated through a series of tests and analyses, including aspects such as time domain, robustness, frequency domain, and evaluation of nonlinearity effects. The simulation results are compared between the proposed DO-SFOPID control technique and the fractional-order PID (FOPID) and sigmoid-based PID (SPID) control techniques, both of which have been tuned using different metaheuristic algorithms that have gained significant recognition in recent years. As a result of these comparative analyses, the superiority of the DO-SFOPID control technique is confirmed as it shows an improved performance with respect to the other control techniques. Furthermore, the performance of the proposed DO-SFOPID control technique is validated within an experimental setup for the AVR system. The simulation results show that the proposed DO-SFOPID control technique is highly successful in terms of stability and robustness. In summary, this study provides comprehensive evidence supporting the effectiveness and superiority of the DO-SFOPID control technique on the AVR system through both simulation and experimental results. [ABSTRACT FROM AUTHOR]

Petroleum reservoirs are often influenced by various flow behaviours including the mixture of gas, water and oil. The gas relative permeability is used to estimate how much of the gas in the reservoir is producible at a given water saturation level. Therefore, the gas relative permeability is a significant parameter to characterize the behaviour of petroleum reservoirs. However, the measurement of gas relative permeability by traditional methods tends to be comparatively expensive and time-consuming. In the recent years, the machine learning techniques provided new alternatives for predicting the gas relative permeability. For this purpose, five new methods were proposed based on kernel extreme learning machine (KELM) technique. Five meta-heuristic algorithms were adopted to tune the model hyper-parameters of KELMs, i.e., butterfly optimization algorithm (BOA), tunicate swarm algorithm (TSA), Multi-verse optimizer (MVO), Golden jackal optimization (GJO) and Harris hawk's optimization (HHO). Five-fold cross validation was used to increase the model generalization. An extensive dataset from the experiments which contain 1024 data were taken to develop models. Four classical statistical indicators were used to measure the model performance, i.e., root mean squared error (RMSE), coefficient of determination (R2), variance accounted for (VAF) and mean absolute error (MAE). In addition, two comprehensive manners, overall evaluation index (GI) and Taylor Diagram, were evaluated to provide overall model assessments. Proposed hybrid KELM models performed better than several other machine learning techniques. BOA-KELM model with swarm size 150 generated the best generalization for the testing set and could be recommended to predict the gas relative permeability with the same inputs used in this study. The detailed performance of BOA-KELM includes: training set (GI:0.1736; R2: 0.9902; RMSE: 0.7477; VAF: 99.0218; MAE: 10.6636), testing set (GI:0.4164; R2: 0.9789; RMSE: 0.5314; VAF: 97.8917; MAE: 4.1706). The mutual information technique was employed to examine the influence of influential factors to the model interpretation and it can be found that the gas saturation had a larger influence on the hybrid KELM models. When it was used as an individual input, the overall prediction decreased but acceptable prediction performance still can be obtained by hybrid KELM models. In the case of the gas saturation to be the only input, the best testing R2 (0.94) could be generated by MVO-KELM which is higher than the R2 from the empirical method named Corey-Brooks model and several other machine learning techniques. The main novelty of this study is that five new machine learning methods were proposed to predict the gas relative permeability and performed better than other empirical or machine learning techniques. Highlights: Five new methods based on KELM were proposed to predict gas relative permeability in reservoir. Meta-heuristic algorithms were used to tune the hyper-parameters in KELM. BOA-KELM model with swarm size 150 brought the best generalization ability. Hybrid KELM models performed better than other classical and machine learning model for multi-inputs. Mutual information was used to explore the interpretation of inputs. [ABSTRACT FROM AUTHOR]

This paper proposes a new meta-heuristic optimization algorithm called Cleaner Fish Optimization algorithm (CFO) inspired by cleaner fish. The CFO simulates the movement behavior of cleaner fish when performing "cleaning services" and the behavior of female may change its sex to become a male, and defines two modes of position update. In addition, a two-generation cycle operation strategy is proposed to realize the optimization process. To verify the effectiveness of the CFO algorithm, 23 well-known CEC benchmark functions, CEC-2017 benchmark functions and 4 engineering design problems are adopted. Simulation results show that the proposed algorithm has a faster convergence rate and better optimal solution when it compared with several other meta-heuristic algorithms. [ABSTRACT FROM AUTHOR]

Lung cancer causes millions of deaths annually, and CT scans and lung X-rays are common diagnostic tools. However, large datasets can contain noisy and irrelevant features that can affect the effectiveness of deep learning classification systems. Feature selection is a preprocessing step that can minimize database dimensionality and improve classification accuracy by selecting essential features. In addition, to solve the disadvantage of expensive solution set analysis in the wrapper technique, this study offers an efficient evaluation methodology that significantly decreases the evaluation cost and enhances the efficacy of the feature selection method. Hence, the study proposed a Hybrid Spotted Hyena Optimization with Seagull Algorithm to solve feature selection problems, which efficiently obtained the optimum subset with the largest number of relevant attributes. Biomedical lung data are collected from the LIDC/IDRI and chest X-ray datasets, and the bicubic-interpolation approach is employed to eliminate noise present in the data. We used generative modeling technique, DCGAN, to perform data augmentation. The chosen lung characteristics are evaluated using a hybrid CNN-LSTM, which identified normal and abnormal features in biomedical lung data. The system's efficacy is determined by examining its accuracy, precision, recall, specificity, and sensitivity using a Python experimental design. In the LIDC/IDRI database, the proposed classifier achieved a sensitivity of 99.8%, specificity of 99.3%, precision of 99.14%, and accuracy of 99.6%. In the chest X-ray dataset, the classifier achieved a sensitivity of 99.62%, specificity of 97.8%, precision of 97.5%, and accuracy of 99.7%. [ABSTRACT FROM AUTHOR]

The uniaxial compressive strength (UCS) is an essential parameter to study rock characteristics, determined by direct and indirect methods. However, the direct methods of determining rock UCS are lengthy and arduous, presenting a requirement of developing a robust indirect method. This investigation introduces an optimal computational model based on the artificial intelligence approach. For that aim, the relevance vector machine (RVM) and long short-term memory (LSTM) approaches have employed 24 computational models in estimating rock UCS and introducing an optimal computational model. The 514, 146, and 74 data points have trained, tested, and validated the 24 models compiled from the literature. The model comparison reveals that implementing a secondary kernel function in a single kernel-based RVM model enhances the performance. Moreover, the particle swarm (PSO) optimized dual kernel-based RVM model attains higher performance than genetic (GA) optimized RVM models. Conversely, the Adam-optimized LSTM model achieved higher performance than other LSTM models. The overall comparison introduces model MD21 (PSO-optimized RVM model implemented by dual kernels, i.e., Laplacian + polynomial) as an optimal performance model in predicting rock UCS with a correlation coefficient of 0.9979 (in the testing phase) and 0.9939 (in the validation phase). In addition, the multicollinearity analysis reveals that the database variables consist of weak multicollinearity. It is noted that the optimized RVM and LSTM models attain overfitting because of weak multicollinearity and optimization algorithms. The analysis of variance (ANOVA), Z, and Anderson–Darling tests accept the research hypothesis for the compiled database. In addition, the trend of simulated results illustrates the robustness and correctness of the employed model MD21. Highlights: Implementation of hybrid relevance vector machine and long short-term memory computational models to assess uniaxial compressive strength of rock. Comparison of genetic and particle swarm optimized relevance vector machine model to find the best optimization algorithm. Comparison of Adam, root-mean-square proportion, and stochastic gradient descent with momentum optimized long short-term memory models. Illustration of the effect of multicollinearity on performance and curve fitting of optimized computational models. Particle swarm optimized dual kernel-based relevance vector machine is an optimal computational model for assessing rock strength. [ABSTRACT FROM AUTHOR]

Recently, light fidelity (Li-Fi) technology becomes important for rapid data transmission in the network. Integration of different communication technologies can be used to address the traffic limitations posed by increasing number of Internet users. Hybrid Wi-Fi/Li-Fi networks (HLWN) make use of rapid Li-Fi data transmission and Wi-Fi coverage So, the combination of them can resolve the limitations of both technologies and enhance the efficiency of the overall network. At the same time, the choice of access point (AP) remains a difficult task as the coverage regions of various networks overlapped with one another. Based on instant channel data, the traditional load balancing schemes allocate every client to a certain AP, offering the optimum solutions at a time instance. But it can results in several handoffs for clients and degrade the throughput performance. Therefore, this article develops a Mobility aware LB using Kho–Kho optimization algorithm (MALB-KKOA) for HLWN. The presented MALB-KKOA technique is investigated in two aspects such as It is permissible to have both several AP associations (MA) and a single AP association (SA) (MA). In the SA phase, every client is aided by an AP either Li-Fi or Wi-Fi where the MALB-KKOA model allocates every client to a particular network over a time duration to reduce handover. On the other hand, in the MA phase, every client is concurrently assisted by Li-Fi as well as Wi-Fi, and no vertical handover takes place. In addition, the MALB-KKOA model is mainly based on the approaches utilized by the players in a tag-team game named Kho–Kho. Moreover, the MALB-KKOA model computes an objective function for the minimization of packet loss and delay. The experimental validation of the MALB-KKOA model is tested and the results signified its promising performance over other recent approaches. [ABSTRACT FROM AUTHOR]

Anomaly detection (AD) in the industrial internet of things (IIoT) platform is said to be the major module of security the consistency, safety, and efficacy of industrial procedures. In IIoT, several sensors and devices always gather massive data counts from tools, infrastructure, and equipment. Ensuring the safety of IIoT AD systems is vital for protecting against cyber-attacks. AD and Intrusion detection are required to work in tandem to maintain industrial procedures. Machine learning (ML) and deep learning (DL) approaches generally employed for AD in IIoT. These methods allow automated AD and pattern detection. With this motivation, this study develops an enhanced pelican optimization model with an ensemble voting-based anomaly detection (EPOA-EVAD) approach. Primarily, the SMOTE approach is used for class imbalance data handling. The presented EPOA-EVAD technique integrates the EPOA-based feature selection and ensemble voting classifier to enhance the accuracy and efficiency of AD in IIoT environments. In addition, the group teaching optimization algorithm with SMOTE approach is used for the purpose of class imbalance data handling. EPOA optimally chooses the related features from the complex and high-dimensional IIoT data. For AD, the EPOA-EVAD technique involves an ensemble learning process comprising gated recurrent unit (GRU), bi-directional long short-term memory (BiLSTM), and stacked autoencoder (SAE). Lastly, the seagull optimization (SGO) algorithm fine-tunes the parameters compared with the DL approaches. The simulation values exhibited that the proposed system outperforms standard approaches, offering robust and adaptive AD capabilities in dynamic IIoT settings. The proposed EPOA-EVAD technique contributes to the advancement of AD techniques crucial for maintaining the integrity and efficiency of industrial processes in the era of IIoT. [ABSTRACT FROM AUTHOR]

The optimal reactive power dispatch (ORPD) problem is a critical factor in maintaining the safe and efficient operation of electric networks. Due to its mixed-variable nonlinear nature, addressing this problem requires an appropriate optimization algorithm. In this study, a novel approach based on the combination of artificial rabbits optimization (ARO) and gradient-based optimization (GBO) algorithms was proposed to solve the ORPD problem in electric networks. The performance of the proposed AROGBO algorithm were verified on 7 numerical optimization test functions. To evaluate the effectiveness of this hybrid AROGBO technique, standard IEEE-30, IEEE-57 bus, and IEEE-118 bus test systems were employed, with two objective functions tested for each system: minimum total power loss and minimum total voltage deviations. The AROGBO, ARO, and GBO algorithms were utilized in each case to determine the optimal values of the generator voltage, transformer tap changer positions, and reactive power compensation values. A comprehensive comparison was made between the results obtained from the hybrid AROGBO algorithm, standard ARO and GBO algorithms, and other metaheuristic optimization techniques. The simulation attainments verify the accuracy and stability of the proposed AROGBO methodology in solving the ORPD problem. [ABSTRACT FROM AUTHOR]

In this paper, a new algorithm named the improved transient search optimization algorithm (ITSOA) is utilized to solve classical test functions, optimize the consumption of building energy, and optimize hybrid energy system production. The conventional TSOA draws inspiration from the fleeting behavior of electrical circuits with energy storage components. Rosenbrock's direct rotation technique is used to improve the traditional TSOA performance against exploration and exploitation unbalance. First, the ITSOA performance is investigated in solving 23 classical benchmark functions, and the outcomes have shown the superior capability of the recommended algorithm in comparison with the conventional TSOA, DMO, SHO, GA, MRFO, and PSO methods. Also, the ITSOA proficiency is verified in solving the building energy optimization (BEO) problem for minimizing the energy usage of two simple and detailed buildings. The optimization results showed that the optimized solutions of ITSOA in single and multi-objective optimizations compared to conventional TSOA, DMO, SHO, GA, MRFO, and PSO obtained a lower value of the cost function. Also, the superiority of ITSOA has been confirmed to solve the BEO compared to previous methods. Moreover, the multi-objective optimization results have shown that ITSOA is able to determine the ultimate solution among the Pareto front set based on the fuzzy decision-making approach and building energy utilization decisions. [ABSTRACT FROM AUTHOR]

In this paper, a novel Moth-Flame Optimization (MFO) algorithm, namely MFO algorithm enhanced by Multiple Improvement Strategies (MISMFO) is proposed for solving parameter optimization in Multi-Kernel Support Vector Regressor (MKSVR), and the MISMFO-MKSVR model is further employed to deal with the software effort estimation problems. In MISMFO, the logistic chaotic mapping is applied to increase initial population diversity, while the mutation and flame number phased reduction mechanisms are carried out to improve the search efficiency, as well the adaptive weight adjustment mechanism is used to accelerate convergence and balance exploration and exploitation. The MISMFO model is verified on fifteen benchmark functions and CEC 2020 test set. The results show that the MISMFO has advantages over other meta-heuristic algorithms and MFO variants in terms of convergence speed and accuracy. Additionally, the MISMFO-MKSVR model is tested by simulations on five software effort datasets and the results demonstrate that the proposed model has better performance in software effort estimation problem. The Matlab code of MISMFO can be found at https://github.com/loadstar1997/MISMFO. [ABSTRACT FROM AUTHOR]

The limited energy possessed by each individual sensor node makes the process of designing and developing an efficient wireless sensor network as a herculean task. The process of clustering and successive cluster head (CH) process with energy efficiency is essential for extending network lifetime and sustaining the existence of alive sensor nodes in the network. In this paper, a multi-objective optimization algorithm based on Hybrid Bald Eagle Search Optimization Algorithm (HBESAOA) is presented as the energy clustering solution for targeting on the process of extending the sensor nodes' network lifetime. This multi-objective optimization HBESAOA algorithm included the fitness evaluating factors of energy, delay, distance, node centrality and node degree into account during the process of CH selection. It specifically adopted the well-balanced exploration and exploitation capabilities of Bald Eagle Search (BES), such that potential search process during clustering and subsequent CH selection is attained in the network. It is prevented with the potential of attaining maximized solution diversity with prevented premature convergence problem. The results of this HBESAOA scheme is identified to be significant in increasing the mean network lifetime by 26.78%, compared to the baseline CH selection schemes independent to the position of the sink node. The energy sustenance in the network is also predominantly improved by 21.98%, independent to the scalable increase in the number of sensor nodes on comparison with the competitive approaches used for evaluation. [ABSTRACT FROM AUTHOR]

Parameter identification of solar photovoltaic (PV) cells is crucial for the PV system modeling. However, finding optimal parameters of PV models is an intractable problem due to the highly nonlinear characteristics between currents and voltages in different environments. To address this problem, whale optimization algorithm (WOA)-based meta-heuristic algorithm has turned out to be a feasible and effective approach. As a highly promising optimization algorithm, different enhanced WOA variants have been proposed. Nevertheless, there has been no comparative study of WOA and its variants for parameter identification of PV models so far. To further investigate and analyze the performance of WOA in the studied problem, this work applied and compared WOA and ten enhanced WOA variants for identifying five PV model parameters. Different evaluation indices including solution accuracy, search robustness, and convergence curve were employed to reveal their performance variation. Based on the simulation results, a multi-model statistical analysis with the Friedman test at a confidence level 0.05 was conducted to rank all algorithms. EWOA that hybridizes the sorting-based differential mutation operator and the Lévy flight strategy ranked first and its performance was further verified. Besides, according to the simulation results, possible effective improvement directions for WOA in tackling this intractable problem are concluded to guide future work. [ABSTRACT FROM AUTHOR]

Global optimization techniques are increasingly preferred over human-driven methods in the design of electromagnetic structures such as metasurfaces, and careful construction and parameterization of the physical structure is critical in ensuring computational efficiency and convergence of the optimization algorithm to a globally optimal solution. While many design variables in physical systems take discrete values, optimization algorithms often benefit from a continuous design space. This work demonstrates the use of level set functions as a continuous basis for designing material distributions for metasurface arrays and introduces an improved parameterization which is termed the periodic level set function. We explore the use of alternate norms in the definition of the level set function and define a new pseudo-inverse technique for upsampling basis coefficients with these norms. The level set method is compared to the fragmented parameterization and shows improved electromagnetic responses for two dissimilar cost functions: a narrowband objective and a broadband objective. Finally, we manufacture an optimized level set metasurface and measure its scattering parameters to demonstrate real-world performance. [ABSTRACT FROM AUTHOR]

Harris Hawks optimization (HHO) algorithm was a powerful metaheuristic algorithm for solving complex problems. However, HHO could easily fall within the local minimum. In this paper, we proposed an improved Harris Hawks optimization (IHHO) algorithm for solving different engineering tasks. The proposed algorithm focused on random location-based habitats during the exploration phase and on strategies 1, 3, and 4 during the exploitation phase. The proposed modified Harris hawks in the wild would change their perch strategy and chasing pattern according to updates in both the exploration and exploitation phases. To avoid being stuck in a local solution, random values were generated using logarithms and exponentials to explore new regions more quickly and locations. To evaluate the performance of the proposed algorithm, IHHO was compared to other five recent algorithms [grey wolf optimization, BAT algorithm, teaching–learning-based optimization, moth-flame optimization, and whale optimization algorithm] as well as three other modifications of HHO (BHHO, LogHHO, and MHHO). These optimizers had been applied to different benchmarks, namely standard benchmarks, CEC2017, CEC2019, CEC2020, and other 52 standard benchmark functions. Moreover, six classical real-world engineering problems were tested against the IHHO to prove the efficiency of the proposed algorithm. The numerical results showed the superiority of the proposed algorithm IHHO against other algorithms, which was proved visually using different convergence curves. Friedman's mean rank statistical test was also inducted to calculate the rank of IHHO against other algorithms. The results of the Friedman test indicated that the proposed algorithm was ranked first as compared to the other algorithms as well as three other modifications of HHO. [ABSTRACT FROM AUTHOR]

This paper introduces a novel meta-heuristic algorithm named Rhinopithecus Swarm Optimization (RSO) to address optimization problems, particularly those involving high dimensions. The proposed algorithm is inspired by the social behaviors of different groups within the rhinopithecus swarm. RSO categorizes the swarm into mature, adolescent, and infancy individuals. Due to this division of labor, each category of individuals employs unique search methods, including vertical migration, concerted search, and mimicry. To evaluate the effectiveness of RSO, we conducted experiments using the CEC2017 test set and three constrained engineering problems. Each function in the test set was independently executed 36 times. Additionally, we used the Wilcoxon signed-rank test and the Friedman test to analyze the performance of RSO compared to eight well-known optimization algorithms: Dung Beetle Optimizer (DBO), Beluga Whale Optimization (BWO), Salp Swarm Algorithm (SSA), African Vultures Optimization Algorithm (AVOA), Whale Optimization Algorithm (WOA), Atomic Retrospective Learning Bare Bone Particle Swarm Optimization (ARBBPSO), Artificial Gorilla Troops Optimizer (GTO), and Harris Hawks Optimization (HHO). The results indicate that RSO exhibited outstanding performance on the CEC2017 test set for both 30 and 100 dimension. Moreover, RSO ranked first in both dimensions, surpassing the mean rank of the second-ranked algorithms by 7.69% and 42.85%, respectively. Across the three classical engineering design problems, RSO consistently achieves the best results. Overall, it can be concluded that RSO is particularly effective for solving high-dimensional optimization problems. [ABSTRACT FROM AUTHOR]

This study examined the optimal size of an autonomous hybrid renewable energy system (HRES) for a residential application in Buea, located in the southwest region of Cameroon. Two hybrid systems, PV-Battery and PV-Battery-Diesel, have been evaluated in order to determine which was the better option. The goal of this research was to propose a dependable, low-cost power source as an alternative to the unreliable and highly unstable electricity grid in Buea. The decision criterion for the proposed HRES was the cost of energy (COE), while the system's dependability constraint was the loss of power supply probability (LPSP). The crayfish optimization algorithm (COA) was used to optimize the component sizes of the proposed HRES, and the results were contrasted to those obtained from the whale optimization algorithm (WOA), sine cosine algorithm (SCA), and grasshopper optimization algorithm (GOA). The MATLAB software was used to model the components, criteria, and constraints of this single-objective optimization problem. The results obtained after simulation for LPSP of less than 1% showed that the COA algorithm outperformed the other three techniques, regardless of the configuration. Indeed, the COE obtained using the COA algorithm was 0.06%, 0.12%, and 1% lower than the COE provided by the WOA, SCA, and GOA algorithms, respectively, for the PV-Battery configuration. Likewise, for the PV-Battery-Diesel configuration, the COE obtained using the COA algorithm was 0.065%, 0.13%, and 0.39% lower than the COE provided by the WOA, SCA, and GOA algorithms, respectively. A comparative analysis of the outcomes obtained for the two configurations indicated that the PV-Battery-Diesel configuration exhibited a COE that was 4.32% lower in comparison to the PV-Battery configuration. Finally, the impact of the LPSP reduction on the COE was assessed in the PV-Battery-Diesel configuration. The decrease in LPSP resulted in an increase in COE owing to the nominal capacity of the diesel generator. [ABSTRACT FROM AUTHOR]

The concept of computational intelligence (CI)-based optimization algorithms emerged in the early 1960s as a more practical approach to the contemporary derivate-based approaches. This paved the way for many modern algorithms to arise with an unprecedented growth rate in recent years, each claiming to have a novel and present a profound breakthrough in the field. That said, many have raised concerns about the performance of these algorithms and even identified fundamental flaws that could potentially undermine the integrity of their results. On that note, the premise of this study was to replicate some of the more prevalent, fundamental components of these algorithms in an abstract format as a measure to observe their behavior in an isolated environment. Six pseudo algorithms were designed to create a spectrum of intelligence behavior ranging from absolute randomness to local search-oriented computational architecture. These were then used to solve a set of centered and non-centered benchmark suites to see if statistically different patterns would emerge. The obtained result clearly highlighted that the algorithm's performance would suffer significantly as these benchmarks got more intricate. This is not just in terms of the number of dimensions in the search space but also the mathematical structure of the benchmark. The implication is that, in some cases, sheer processing resources can mask the algorithm's lack of sufficient intelligence. But as importantly, this study attempted to identify some mechanics and concepts that could potentially cause or amplify this problem. For instance, the excessive use of greedy strategy, a prevalent measure embedded in many modern CI-based algorithms, has been identified as potentially one of these reasons. The result, however, highlights a more fundamental problem in the CI-based optimization field. That is, these algorithms are often treated as a black box. This perception cultivated the culture of not exploring the underlying structure of these algorithms as long as they were deemed capable of generating acceptable results, which permits similar biases to go undetected. [ABSTRACT FROM AUTHOR]

This article explores the use of different metaheuristic optimization algorithms for training a self-organizing neural network (SONN) model to estimate Brazilian tensile strength (BTS) in granite rocks, including brainstorm optimization (BSO), coronavirus herd immunity optimization (CHIO), and social ski-driver optimization (SSDO). The optimization processes of the algorithms were similar, and the same population size and maximum iterations were used based on 284 granite samples collected. The Schimidt hammer test (Rn), point load test (IS50), and dry density test (DD) based on the ISRM standards were considered to predict BTS. Accordingly, 80% of the whole dataset (approximately, 228 samples) was used to train the intelligence models, while the remaining 20% was used for testing the trained performance of the models. Tenfold cross-validation with three repeats was applied to avoid the overfitting phenomena. While the BSO–SONN demonstrated excellent performance on both training and testing datasets with low MAE and RMSE values and a high R2 (MAE = 0.164, RMSE = 0.201, R2 = 0.974 on the training dataset, MAE = 0.179, RMSE = 0.231, R2 = 0.970 on the testing dataset), the CHIO–SONN also performed well, but it had higher MAE and RMSE values compared to BSO–SONN. However, it still has a good R2 (MAE = 4.212, RMSE = 4.555, R2 = 0.897 on the training dataset, MAE = 3.984, RMSE = 4.379, R2 = 0.904 on the testing dataset), and the SSDO–SONN showed lower performance, especially in terms of R2 (MAE = 1.295, RMSE = 1.545, R2 = 0.261 on the training dataset, MAE = 1.325, RMSE = 1.574, R2 = 0.156 on the testing dataset), indicating that the model might not be capturing the variation in the data well. Another conventional machine learning model, namely support vector machine (SVM), was also applied and compared to the metaheuristic algorithm-optimized models. The SVM's results showed that it performs reasonably well, with good R2 values (MAE = 0.183, RMSE = 0.357, R2 = 0.907 on the training dataset, MAE = 0.292, RMSE = 0.646, R2 = 0.761 on the testing dataset). However, its MAE and RMSE are slightly higher compared to BSO–SONN. As a result, the BSO–SONN model still outperformed all other models in both training and testing datasets, providing the most accurate and reliable predictions of BTS values with the accuracy approximately 97% in practical engineering. The SSDO–SONN model lags behind in terms of R2, suggesting that it may need further improvement. Sensitivity analysis results also suggested that Rn has the highest importance for the BSO–SONN model in predicting BTS. Highlights: Self-organizing neural network is a promising technique to estimate Brazilian tensile strength of rock mass. The Schimidt hammer test, point load test and dry density test based on the ISRM standards were considered to predict Brazilian tensile strength of rock mass. Three hybrid intelligence models were developed for rapid estimating Brazilian tensile strength of rock mass in practical engineering. Brainstorm optimization algorithm provided a robust efficiency in improving the accuracy of the self-organizing neural network with an accuracy of 97%. [ABSTRACT FROM AUTHOR]

Optimization techniques, particularly meta-heuristic algorithms, are highly effective in optimizing and enhancing efficiency across diverse models and systems, renowned for their ability to attain optimal or near-optimal solutions within a reasonable timeframe. In this work, the Puma Optimizer (PO) is proposed as a new optimization algorithm inspired from the intelligence and life of Pumas in. In this algorithm, unique and powerful mechanisms have been proposed in each phase of exploration and exploitation, which has increased the algorithm's performance against all kinds of optimization problems. In addition, a new type of intelligent mechanism, which is a type of hyper-heuristic for phase change, is presented. Using this mechanism, the PO algorithm can perform a phase change operation during the optimization operation and balance both phases. Each phase is automatically adjusted to the nature of the problem. To evaluate the proposed algorithm, 23 standard functions and CEC2019 functions were used and compared with different types of optimization algorithms. Moreover, using the statistical test T-test and the execution time to solve the problem have been discussed. Finally, it has been tested using four machine learning and data mining problems, and the results obtained from all the analysis signifies the excellent performance of this algorithm against all kinds of problems compared to other optimizers. This algorithm has performed better than the compared algorithms in 27 benchmarks out of 33 benchmarks and has obtained better results in solving the clustering problem in 7 data sets out of 10 data sets. Furthermore, the results obtained in the problems of community detection and feature selection and MLP were superior. The source codes of the PO algorithm are publicly available at https://www.mathworks.com/matlabcentral/fileexchange/157231-puma-optimizer-po. [ABSTRACT FROM AUTHOR]

Internet of Things (IoT) technology has facilitated different human-related activities and, therefore, has extended to a wide range of applications. However, these networks have the limited resources that must be utilized in an efficient manner. Hence, various studies have introduced several methods and algorithms for better managing these resources. Although these approaches produce acceptable solutions, their performance still needs improvement because of an increasing number of IoT devices and application services. To address such a limitation, the present study proposed a novel IoT environments-specific bandwidth allocation method, which dynamically distributes the wireless bandwidth among the devices according to their heterogeneous nature and the existence of various traffic services. To this end, the Trader metaheuristic algorithm was developed for the discrete problems and formulated as a multi-objective algorithm. To evaluate the performance of the proposed method, it was applied to the six gold standard datasets generated based on the Poisson distribution. The outcomes indicated that the proposed approach surpasses the other introduced state-of-the-art methods in terms of the service success rate by 6.32%, network throughput by 5.79%, and resource efficiency by 3.13%. The results also showed that based on the different statistical criteria, the proposed discrete metaheuristic algorithm yields better outcomes compared to the other efficient algorithms. [ABSTRACT FROM AUTHOR]

The main resources in software projects are human resources equipped with various skills, which makes software development a typical intelligence-intensive process. Therefore, effective human resource scheduling is indispensable for the success of software projects. The aim of software project scheduling is to assign the right employee to the right activity at the right time. Uncertainty is inevitable in software development, which further complicates the scheduling of projects. We investigate the software project scheduling problem with uncertain activity durations (SPSP-UAD) and aim at obtaining effective scheduling policies for the problem. We present and transform a scenario-based non-linear chance-constrained stochastic programming model into an equivalent linear programming model. To solve the NP-hard SPSP-UAD efficiently, we develop a hybrid meta-heuristic TLBO-GA that combines the teaching–learning-based optimization algorithm (TLBO) and the genetic algorithm (GA). Our TLBO-GA is also equipped with some problem-specific operators, such as population initialization, rows exchange and local search. We use simulation to evaluate the scheduling policies obtained by our algorithms. Extensive computational experiments are conducted to evaluate the performance of our TLBO-GA in comparison to the exact solver CPLEX and four existing meta-heuristic algorithms. The comparative results reveal the effectiveness and efficiency of our TLBO-GA. Our TLBO-GA provides an extensible and adaptive automated scheduling decision support tool for the software project manager in the complex and uncertain software development environment. [ABSTRACT FROM AUTHOR]

This study aims to address the problem of optimal power flow (OPF) in electrical networks by integrating wind power production FACTS devices. The main objectives of this study include minimizing generating costs, reducing power loss, enhancing the voltage profile of the system, and increasing its load ability. In this study, the tuna swarm optimization algorithm (TSO) is utilized as a novel meta-heuristic technique to optimize electrical networks to incorporate FACTS devices and stochastic wind energy production. To account for wind power, a model based on the Weibull probability density function is utilized to identify the optimal values of the decision variables. The study compares several objective functions, including minimization of fuel cost and active power loss across the transmission system, and simulates the test system consisting of TCSC, TCPS, and SVC using the IEEE 30-bus system as a network for examining system parameters. The efficacy of the TSO methodology is explored and compared to other traditional approaches in the paper. The simulation findings of the study show that by lowering the overall power cost and power losses, TSO is more successful in determining the OPF's ideal solution. The results show that the TSO algorithm performs better than driving training-based optimization (DTBO), Coulomb–Franklin's algorithm (CFA), and whale optimization algorithm (WOA) since it can handle more difficult OPF issues with a lower convergence rate. When comparing the four methods, for instance, TSO produced a noticeable improvement. It was able to successfully reduce the cost function to 807.454 $/h which is better than 807.9545 $/h for CFA, 809.4945 for DTBO, and 828.89 $/h for WOA, while lowering the power loss to 1.842 MW which is lower than the losses incurred by CFA, DTBO, and WOA, which are 1.9137 MW, 2.703 MW, and 2.757 MW, respectively. Furthermore, in Case 3, the gross cost reduced to 914.3735 $/h. [ABSTRACT FROM AUTHOR]

In order to mitigate/prevent the risks of landslides, one of the essential tools that can be used to manage and plan the development of human settlements is landslide susceptibility. The two metaheuristic algorithms explored in this paper are the SCE and VSA algorithms used to optimize the artificial neural network (ANN) model. By integrating the two algorithms with the artificial neural network model, we try to determine its optimum computational parameters in order to generate the landslide susceptibility mapping for the Kurdistan province in Iran. Sixteen causative factors of landslides are included in the spatial database. The landslide susceptibility maps were generated in a GIS medium, and in order to evaluate the employed predictive models, the criterion of the area under the curve (AUC) was employed. This investigation includes 1072 landslide events, which are divided as follows: one-third as testing data and two-thirds as training data (i.e., a 75:25 ratio). The results indicate that after using the abovementioned algorithms, the AUC increased noticeably from 0.708 to 0.788 for SCE-MLP and from 0.744 to 0.818 for VSA-MLP in the training phase. The criterion of the area under the curve was utilized in order to evaluate the accuracy of the employed probabilistic models. Incidentally, the comparable AUCs calculated for the VSA-MLP testing databases and the obtained AUCs were 0.818, 0.801, 0.791, 0.786, 0.784, 0.778, 0.777, 0.776, 0.754 and 0.744, respectively for population size in training databases equal to 50, 350, 500, 150, 450, 200, 400, 300, 100 to and 250. Also, in case of SCE-MLP, the training and testing AUC were found (0.878, 0.865, 0.851, 0.850, 0.819, 0.816, 0.815, 0.781, 0.760, and 0.756) and (0.788, 0.782, 0.759, 0.744, 0.727, 0.720, 0.718, 0.713 and 0.708). The best fit for swarm size conditions of the SCE-MLP and VSA-MLP model showed 150 and 350, respectively. The acquired results indicate that the VSA-ANN model has a better predictive capability in optimization of the structure of the artificial neural network model and computational parameters in comparison with the SCE-ANN. [ABSTRACT FROM AUTHOR]

The integration of advanced technologies like cloud and edge computing has facilitated efficient resource coordination, resulting in improved overall management and widespread applicability. Simultaneously, addressing energy consumption, reliability, and server and communication link failure rates has become a pressing research concern. To address this challenge, an advanced combined-decomposition whale optimization algorithm has been developed. This algorithm utilizes a unique combined-decomposition operator to identify nearly optimal server coalitions, enhancing the quality of service performance. Through a training process at various utilization levels, servers determine their optimal utilization for achieving the maximum energy-to-reliability trade-off ratio. Then, a head server with the highest optimal utilization leads each of these clusters of servers. Unlike other population-based clustering methods, this algorithm incorporates the whale optimization algorithm, extending its exploration and exploitation capabilities beyond other leading scheduling algorithms. The integration of these techniques successfully achieves the dual objective of balancing energy and reliability, addressing existing challenges, and ensuring optimal energy-reliability trade-offs. Simulation experiments using various evaluation metrics demonstrate that the proposed approach enhances energy efficiency by approximately 17 to 35% and reliability by 25 to 55%, all while meeting quality service standards. [ABSTRACT FROM AUTHOR]

This article proposes the use of a leader white shark optimizer (LWSO) with the aim of improving the exploitation of the conventional white shark optimizer (WSO) and solving the economic operation-based load dispatch (ELD) problem. The ELD problem is a crucial aspect of power system operation, involving the allocation of power generation resources to meet the demand while minimizing operational costs. The proposed approach aims to enhance the performance and efficiency of the WSO by introducing a leadership mechanism within the optimization process, which aids in more effectively navigating the complex ELD solution space. The LWSO achieves increased exploitation by utilizing a leader-based mutation selection throughout each generation of white sharks. The efficacy of the proposed algorithm is tested on 13 engineer benchmarks non-convex optimization problems from CEC 2020 and compared with recent metaheuristic algorithms such as dung beetle optimizer (DBO), conventional WSO, fox optimizer (FOX), and moth-flame optimization (MFO) algorithms. The LWSO is also used to address the ELD problem in different case studies (6 units, 10 units, 11 units, and 40 units), with 20 separate runs using the proposed LWSO and other competitive algorithms being statistically assessed to demonstrate its effectiveness. The results show that the LWSO outperforms other metaheuristic algorithms, achieving the best solution for the benchmarks and the minimum fuel cost for the ELD problem. Additionally, statistical tests are conducted to validate the competitiveness of the LWSO algorithm. [ABSTRACT FROM AUTHOR]