Search

With the surging energy price and environmental concerns, measures to improve energy efficiency have attracted increasing concerns of the manufacture sector, especially energy-intensive manufacturing industries such as tissue paper mills. Energy-efficiency scheduling, as a novel energy-efficient method, has attracted the attention of an increasing number of researchers in recent years. Drying process is the most energy-intensive production process in tissue paper mills, which has a great energy-saving potential. This paper aims to reduce the energy costs for the tissue paper mill, consisting of processing energy cost and set-up energy cost, through integrating drying process optimization with energy-efficient scheduling. First, the energy cost model and the scheduling model were built. Then, the energy cost of the drying process of every job in a given scheduling problem was optimized using particle swarm optimization (PSO). Afterwards, the energy cost was further optimized using energy-efficiency scheduling. In addition, a hybrid non-dominated sorting genetic algorithm II (NSGA-II) was utilized to solve the energy-efficiency scheduling problem. Finally, several real scheduling problems from a real tissue paper mill were addressed using the proposed approach to demonstrate its effectiveness in energy saving. The experiment result showed that there is a great energy-saving potential in the drying process, accounting for up to 12.53% of the total energy consumption. Moreover, the maximum energy saving ratio of the proposed approach could reach 9.03%. On the whole, the proposed approach can provide a new energy-saving method for tissue paper mills or other manufacturing industries.

Nutritionally enriched pineapple rasgulla can be produced through different methods and visual appearance being the most vital concern for the consumer acceptance. Therefore, total colour difference of the processed products should be optimized for better marketability. The central composite design (CCD) was adopted to design the experimental runs, response surface methodology was implemented to study the predictive models for hot air dried (HA), microwave dried (MW), microwave convective dried (MWC) and freeze dried (FD) pineapple fortified rasgulla along with fresh pineapple pulp (PR) fortified rasgulla. Artificial neural network (ANN) model was developed for all of the above mentioned rasgulla samples and optimization was attained by coupling the ANN model with particle swarm optimization (PSO) methodology. The non-linear rasgulla processing was modeled by using the input parameters like oven temperature (for HA), microwave power level (for MW), drying temperature (for MWC), pineapple percentage, cooking time (for HA, MW, MWC, FD and PR) and output as total colour difference. The optimum results obtained at oven temperature of 58.51 ​°C, 30.27% of pineapple and cooking time of 14.32 ​min (HA); microwave power level of 100 ​W, 35% of pineapple and cooking time of 13.51 ​min (MW); drying temperature of 100 ​°C, 35% of pineapple and cooking time of 15 ​min (MWC); 35% of pineapple for both FD and PR, while the cooking time of 12.57 and 15 ​min for FD and PR respectively.

Removal of heavy metals through biosorption using biomass offers several advantages over other conventional techniques such as low cost, high efficiency, environmentally friendly, etc. In the present article, biosorption of Nickel(II) and Lead(II)was investigated using dried biomass of cyanobacterial consortium. OFAT (one-factor-at-a-time) analysis was used to assess the effect of input parameters on the removal of potentially toxic elements by varying initial metal ion concentration (2–10 mgL−1), adsorbent dose (0.1–1.0 gL-1), pH (for Pb(II): 2–6, for Ni(II): 2–8) and temperature (25°C–45°C) individually, at constant shaking speed of 150 ​rpm. Results showed that removal using biomass attained highest values in as short time as 15 ​min. The investigations also showed the removal is highly effective at lower initial concentrations of heavy metals. Maximum removal of Lead(II) (87.27 ​± ​1.75%) and Nickel(II) (92.57 ​± ​0.77%) was obtained at pH 6 and 45°C and at pH 7 and 25°C, respectively, within 15 ​min with 0.1 gL-1 biomass. Both the Langmuir model and Freundlich model were seen to fit the equilibrium data. Further, Artificial Neural Network was used to model the biosorption process. Subsequently, Particle Swarm Optimization was applied to optimize the operating conditions for the removal of both the metals.

Anaerobic fermentation is a promising means of producing volatile fatty acids (VFAs) from waste activated sludge, and thereby recovering resources from solid wastes. This study developed a modified Anaerobic Digestion Model No. 1 (ADM1) to simulate substrate degradation and the influence of pH on VFAs production. Protein and carbohydrate degradations were compared among three substrate degradation models: first-order kinetics, Monod, and Contois. The Monod model best simulated the soluble protein and carbohydrate degradation, whereas the Contois model best simulated the particle protein and carbohydrate degradation. The improved particle swarm optimization (PSO) proved to be the best algorithm for parameter estimation. Next, we proposed linear equations between hydrolysis kinetic constants and different pH values. The relative errors in the simulation results were very low, indicating that the modified ADM1 can accurately simulate the enhanced generation of VFAs under different pH conditions.

Mobile Edge Computing (MEC), which is the main technology behind 5th Generation (5G) networks, is a nascent paradigm that meets the demands of IoT (Internet of Things) and localized computing. From an end-user point of view, it can be regarded as a refinement of cloud computing and Fog computing. The transfer of computational tasks to the closet MEC servers leads to energy efficiency and low latency. It is important to apply the most suitable policies for scheduling, especially when configuring different modules of an IoT application in MEC. In this paper, three algorithms, namely the heuristic Bald Eagle Search Optimisation [BESO] algorithm, Particle Swarm Optimization algorithm [PSO], and Genetic Algorithm [GA], are presented to carry out heuristic offloading of computational tasks with a view to improving the latency and performance of MEC. However, the most effective algorithm must be adopted to conduct these tasks. As a result, this paper attempts to find an algorithm that is most appropriate for MEC. To demonstrate this. the three algorithms were tested in the Long-Term Evolution [LTE] based Orthogonal frequency-division multiplexing [OFDM] network during a period when the edge nodes had no adequate resources. The performance and efficiency of the three algorithms, BESO, PSO and GA, were determined and compared. After generating the results, the comparative results were evaluated. In terms of offloading the computational tasks, the BESO algorithm was discovered to perform better, with greater energy efficiency and lower latency, than the other two algorithms.

Accurate electric energy metering in micro-grid is one of the most urgent problems in the field of electric energy metering. In order to solve the problem that the lackness of electric energy metering can't be accurately calculated with the existing electric energy compensation algorithm when the electric energy metering device is completely faulty, this paper proposes an electric energy compensation algorithm that is limited in micro-grid and is based on standard particle swarm to optimize the deep belief network. Taking the historical electric energy data of each micro source metering point in micro-grid as an example, it is divided into the training set and the test set, the standard particle swarm optimization algorithm is used to determine the optimal learning layers and learning rate of deep belief network, and the electric energy algorithm model is established. The model verification results show that the proposed algorithm is nearly five times lower than the algorithm based on deep belief network solely. Further engineering case comparison shows that lackness of electric energy metering compensated by the algorithm studied in the paper is closer to the theoretical value, and the error is also less than the traditional average electricity algorithm. The real-time power curve is closer to the theoretical value, and has the higher accuracy.

The difference between load demand in the off-peak and peak period is usually high in the context of Nepal, and the high peak load for a short time is the main reason for insufficiency in electricity, frequent electricity outage, and poor power quality. This paper investigates the effectiveness of the time of use (TOU) strategy to reduce peak demand and to improve power quality. TOU electricity price is one of the electric demand response (DR) strategies, which may motivate the customers to reduce their consumption in peak periods and shift load in the off-peak period, which propel the electricity industry towards a higher efficiency compared to that of common flat prices. In this paper, a process based on an equal step length iteration algorithm is used to obtain an optimal period partition. Using the particle swarm optimization (PSO) algorithm, a TOU-based optimization model is proposed to find the optimal electricity price. Then, its impact on peak demand reduction and voltage fluctuation is analyzed. The impact of TOU price on peak demand reduction is investigated in the hourly load profile of Nepal, which indicates the significant reduction in peak demand. Similarly, the impact on voltage fluctuation is analyzed through a case study of the IEEE 33-bus radial distribution test system, which shows voltage profile is improved.

This paper presents a new Reinforcement Learning (RL)-based control approach that uses the Policy Iteration (PI) and a metaheuristic Grey Wolf Optimizer (GWO) algorithm to train the Neural Networks (NNs). Due to an efficient tradeoff to exploration and exploitation, the GWO algorithm shows good results in NN training and solving complex optimization problems. The proposed approach is compared to the classical PI RL-based control approach using the Gradient Descent (GD) algorithm, and with the RL-based control approach which uses the metaheuristic Particle Swarm Optimization (PSO) algorithm. The experiments are conducted using a nonlinear servo system laboratory equipment. Each approach evaluated on how well it solves the optimal reference tracking control for an experimental servo system position control system. The policy NNs specific to all three approaches are implemented as state feedback with integrator controllers to remove the steady-state control errors and thus ensure the convergence of the objective function. Because of the random nature of metaheuristic algorithms, the experiments for GWO and PSO algorithms are run multiple times and the results are averaged before the conclusions are presented. The experimental results shows that for the control objective considered in this paper, the GWO algorithm represents a better solution compared to GD and PSO algorithms.

A wireless sensor network (WSN) includes more low-cost and less-power sensor nodes. All the sensor nodes are positioned in a particular area and form a wireless network by way of self-organizing. They has the ability to work normally at any of the special or wicked environ that people cannot close. However, the data transmission among nodes in an effective way is almost not possible due to various complex factors. Clustering is a renowned technique to make the transmission of data more effective. The clustering model divides the sensor nodes into various clusters. Every cluster in network has unique cluster head node, which send the information to other sensor nodes in cluster. In such circumstances, it is the key role of any clustering algorithm to choose the optimal cluster head under various constraints like less energy consumption, delay and so on. This paper develops a new cluster head selection model to maximize the lifetime of network as well as energy efficiency. Further, this paper proposes a new Fitness based Glowworm swarm with Fruitfly Algorithm (FGF), which is the hybridization of Glowworm Swarm Optimization (GSO) and Fruitfly Optimization algorithm (FFOA) to choose the best CH in WSN. The performance of developed FGF is compared to other existing methods like Particle swarm Optimization (PSO), Genetic Algorithm (GA), Artificial Bee Colony (ABC), GSO, Ant Lion Optimization (ALO) and Cuckoo Search (CS), Group Search Ant Lion with Levy Flight (GAL-LF), Fruitfly Optimization algorithm (FFOA) and grasshopper Optimization algorithm (GOA) in terms of alive node analysis, energy analysis and cost function and the betterments of proposed work is also proven.

Improved Fractional Order Darwinian Particle Swarm Optimization (FODPSO) has been proposed to identify the parameters of solar PV cells and modules. For this purpose, the traditional PSO algorithm has been adapted and an improved one using the fractional order calculus has been especially designed as well. The proposed FODPSO together with the PSO has been applied in both the single and double diode models to describe the specified PV units for purpose of comparison. To examine the advantages of the proposed FODPSO over conventional PSO, two approaches have been performed; the first approach is implementing the FODPSO and PSO algorithms using input data obtained from previous international publications for different types of PV cells/modules, then comparing the FODPSO algorithm's results to the results of PSO and the other previous optimization techniques that were using the same input data and identical PV cells/modules. The second validation approach is achieved by performing real measurements in outdoor conditions for another two types of PV modules (mono and poly crystalline Silicon) and inserting these measurements' readings as input data to the PSO and FODPSO algorithms. A comparative study has also been done for both algorithms' results. Enhanced results have been achieved using the FODPSO technique. It is worth mentioning that during the development of this work, other efforts have been made with different techniques that may result in similar or even better results, yet this paper is still introducing for the first time the FODPSO technique (as a modified technique of the PSO) as applied on the PV modeling problem, in addition the paper presents the benefits of the proposed FODPSO over the conventional PSO and presents a comparison that shows the superiority of the FODPSO over the conventional PSO.

Robotic manipulators are electronically controlled mechanical devices with several links, which are used to perform any specific task under certain circumstances. However, the vibration of these manipulators can provide a hindrance in the completion of the task. Hence, it is highly essential to model and control these manipulators appropriately to minimize the vibrations. This paper provides a comprehensive review of modelling and control techniques of different types of manipulators such as Single Link Manipulator (SLM), Single-Link flexible Manipulator (SLFM), and manipulator with double link (DLM). Furthermore, this review discusses the merits and demerits of different manipulator models and their control methodologies. Moreover, the utilization of the several optimization algorithms such as Differential Evolution (DE), Cuckoo Search (CSA), the Bat Algorithm (BA), the Particle Swarm Optimization (PSO), the Ant Colony Algorithm (ACA), and so on in controlling the position, velocity, and vibration of the manipulators are explored in this paper.

Lightweight and low-cost wearable magnetic and inertial measurement units (MIMUs) have found numerous applications, such as aerial vehicle navigation or human motion analysis, where the 3D orientation tracking of a rigid body is of interest. However, due to the errors in measurements of gyroscope, accelerometer, and/or magnetometer inside a MIMU, numerous studies have proposed sensor fusion algorithms (SFAs) to estimate the 3D orientation accurately and robustly. This paper contributes to these efforts by performing an experimental comparison among a variety of SFAs. Notably, we compared the estimated orientation of 36 SFAs from the complementary filter and linear/extended/complementary/unscented/cubature Kalman filter families with the reference orientation obtained from a camera motion-capture system. The experimental study included data collection with a foot-worn MIMU where nine participants performed various short- and long-duration tasks. We shared the codes and sample of data in https://www.ncbl.ualberta.ca/codes to enable other researchers to compare their works with the literature toward creating a comprehensive online repository for SFAs. To perform a fair comparison, we used the Particle Swarm Optimization routine to find the optimal adaptive gain tuning scheme for each SFAs, as recommended in the literature. Our experimental results showed that gyroscope static bias removal, in general, showed to be effective in reducing the estimation error of SFAs, specifically during long-duration trials. Moreover, our experimental results identified the SFAs with the highest accuracy from each family. We also reported the execution times for the selected SFAs from each family. This paper is among the first experimental comparison studies which provide such breadth of coverage across various SFAs for tracking orientation with MIMUs.

This paper presents novel models of Soft Computing (SC) Maximum Power Point Tracking (MPPT) controllers for Photo-Voltaic Water Pumping Systems(PVWPS) Based on DC Motor. Also paper discusses and evaluates the performance of the proposed models. The proposed methodology is mainly based on duty cycle prediction of the cuk converter to track the maximum power point (MPP) of the PV array. Indeed of the maximum water flow rate of PVWPS at varying climate conditions must ensure that the motor-pump set operates at MPP. The analytical modeling for the proposed MPPT controller has been implemented to predict the optimal duty cycle of the converter for MPPT achievement within the different operating conditions of solar radiation, ambient temperature, and total static head. Also, different Soft Computing (SC) Algorithms have been implemented and evaluated based on Particle Swarm Optimization (PSO) algorithm, Mine Blast Algorithm (MBA), and β -hill climbing ( β -HC) algorithm. A comparative study between SC Algorithms, analytical modeling, and experimental works are given. Also evaluations of SC Algorithms are done to verify SC Algorithms’ accuracy. This evaluation study has proven the significant improvement of daily water flow rate and also has specified the appropriateness of the SC algorithm for MPPT for a PVWPS.

Bacterial foraging algorithm comes from the best survival selection mechanism of animals in nature. As the representative of the heuristic algorithm, the bacterial foraging algorithm has unique advantages in solving the multi difficulty scheduling problem effectively. In order to realize the artificial intelligent management of the enterprise’s staff scheduling, this paper constructs the knowledge staff scheduling model by using a bacterial foraging algorithm and analyzes the implementation principle, advantages, and disadvantages of the algorithm. The influence of the basic parameters in the algorithm model on the algorithm performance is analyzed. In order to optimize the unconventional foraging strategy, the improvement measures of bacterial foraging behavior were proposed. Finally, the performance of the optimized bacterial foraging algorithm is tested and compared with the basic bacterial foraging algorithm, genetic algorithm, and particle swarm optimization algorithm. The experimental results show that the optimized bacterial foraging algorithm can achieve better convergence accuracy and shorter convergence speed for the objective function, and it can solve the scheduling optimization problem of knowledge workers more quickly, accurately, and effectively. The research in this paper shows that the optimization of four aspects of the basic bacterial foraging algorithm improves the performance of the algorithm and provides a theoretical reference for the optimization of the bacterial foraging algorithm.

Objective By optimizing the extreme learning machine network with particle swarm optimization, we established a syndrome classification and prediction model for primary liver cancer (PLC), classified and predicted the syndrome diagnosis of medical record data for PLC and compared and analyzed the prediction results with different algorithms and the clinical diagnosis results. This paper provides modern technical support for clinical diagnosis and treatment, and improves the objectivity, accuracy and rigor of the classification of traditional Chinese medicine (TCM) syndromes. Methods From three top-level TCM hospitals in Nanchang, 10,602 electronic medical records from patients with PLC were collected, dating from January 2009 to May 2020. We removed the electronic medical records of 542 cases of syndromes and adopted the cross-validation method in the remaining 10,060 electronic medical records, which were randomly divided into a training set and a test set. Based on fuzzy mathematics theory, we quantified the syndrome-related factors of TCM symptoms and signs, and information from the TCM four diagnostic methods. Next, using an extreme learning machine network with particle swarm optimization, we constructed a neural network syndrome classification and prediction model that used “TCM symptoms + signs + tongue diagnosis information + pulse diagnosis information” as input, and PLC syndrome as output. This approach was used to mine the nonlinear relationship between clinical data in electronic medical records and different syndrome types. The accuracy rate of classification was used to compare this model to other machine learning classification models. Results The classification accuracy rate of the model developed here was 86.26%. The classification accuracy rates of models using support vector machine and Bayesian networks were 82.79% and 85.84%, respectively. The classification accuracy rates of the models for all syndromes in this paper were between 82.15% and 93.82%. Conclusion Compared with the case of data processed using traditional binary inputs, the experiment shows that the medical record data processed by fuzzy mathematics was more accurate, and closer to clinical findings. In addition, the model developed here was more refined, more accurate, and quicker than other classification models. This model provides reliable diagnosis for clinical treatment of PLC and a method to study of the rules of syndrome differentiation and treatment in TCM.

This paper proposes an adaptive and robust adaptive control strategy based on type-2 fuzzy neural network (T2FNN) for tracking the desired trajectories of a quadrotor. The designed methods can control both the position and the orientation of a quadrotor. Contrary to common sliding mode controllers (SMCs), the robust adaptive trajectory tracking scheme presented here is based on SMC with exponential reaching law; which helps reduce the phenomenon of chattering. Moreover, parameters including the gains of sliding surfaces, are optimized by cuckoo optimization algorithm (COA), and the results are compared with those obtained by genetic algorithm (GA), particle swarm optimization (PSO), ant colony optimization (ACO). The designed methods in this study are called adaptive T2FNN controller and the exponential SMC (ESMC)-T2FNN. The law for updating the T2FNN is obtained online by using the Lyapunov stability theory. Considering undesired factors such as uncertainties, external disturbances and control signal saturation, the results of our controllers are compared with those of the adaptive type-1 fuzzy neural network controller (T1FNN) and ESMC-T1FNN. The extensive simulations demonstrate the effectiveness of the proposed COA-based ESMC-AT2FNN approach compared to the other tested techniques (i.e. GA, PSO and ACO) in terms of the improved transient and steady-state trajectory-tracking performance. The mean and standard deviation values concerning the COA are obtained through statistical analyses at 0.00006173 and 0.000092, respectively. This paper also examines the complexity of COA in optimizing the trajectory tracking control of quadrotor and investigates the effects of COA parameters on optimization results. The stable performance of the cuckoo algorithm is demonstrated by varying its parameters and analyzing the obtained results. These results also show the convergence of COA for the considered problem.

In order to effectively test the performance of the wind turbine during the blade fatigue test with a resonant type of exciting approach, it is important to moment-match the test moment to the target moment. The distribution of the moments on the critical sections can be adjusted by using additional masses that are reasonably located on these sections, but that have different location, number and size options. Achieving this through the traditional trial-and-error method however, which attempts to find the best additional mass variables combination for optimal moment-matching, requires an extremely heavy artificial workload, as the combination options for the additional mass variables are many. To tackle this dilemma, FEA (Finite Element Analysis) associated with PSO (Particle Swarm Optimization) method is now commonly used for moment prediction and optimal combination searching. Nonetheless, the enlargement of the blade scale has meant that using FEA poses some disadvantages, which in turn means an increased amount of time needed for integrated-parameters computing. Moreover, pre-computing work, such as physical object modeling, grid generation & checking, solution setting & parameter adjusting, may also require lots of time and a heavy reliance on professional workers to carry out processing tasks – requirements that are adverse to realizing an automatic dealing procedure. Fortunately, in the blade design and factory leaving stages, those important blade parameters are already defined in a lumped manner. This therefore leads to an applicative use of TMM (Transfer Matrix Method) as when outputting the section data, including moment, it only requires these section parameters for the modeling and the moment-matching process. It is reasonable to believe that FEA usually offers better computing accuracy, while it is also understandable that for the present condition cloud and after describing the lumped definition manner, TMM also presents sufficient accuracy. For the present case study, TMM shows satisfactory prediction accuracy when compared with the test results, with a relative error of no more than 1% for any critical blade section. Additionally, moment-matching optimization work has been conducted by combining with the PSO procedure. The optimal variables combination is finally confirmed with two additional masses of 4000 kg and 605.6 kg located 25m and 48m from the blade root section respectively, which obtains the minimum standard of 4.25%, a higher matching precision compared with that of the test which had 5.6%. Thus, it seems that the TMM-associated PSO method introduced in this paper provides a more efficient way to figure out the optimal variables combination for moment-matching while maintaining sufficient computational precision. In addition, since the strict requirements for moment-matching accuracy have not yet been officially issued, the present case study does not treat the additional mass number as a variable but as the constant 2. Compared with the test however, this paper's result still shows improvements in moment-matching accuracy while also reducing the installing workload needed for the 2 additional masses.

Along the line of waste electrical and electronic equipment (WEEE) recovery, customers are the ultimate decision-makers to determine the destinies of the end-of-life (EoL) electronic products. However, inadequacies exist and those are WEEE collection and generation predictions considering uncertain customers’ behavior and deepening discussion of the influence discrepancies of customers’ behavior between an advanced and a fledging recovery system. To bridge these research gaps, this paper aims to propose a customer-centric approach to forecasting the WEEE collection and generation amounts in Taiwan (i.e., a developed recovery system) and Vietnam (i.e., an developing recovery system), respectively, and analysing the influence disparities from these two societies. First, the combination of grey relational analysis (GRA) and principal component analysis (PCA) is employed to deal with factors reflecting customers’ behavior. Second, the forecast model, the grey neural network (NN) optimized by the particle swarm optimization (PSO) and genetic algorithm (GA), is developed to estimate the collection and generation amounts of waste home appliances during 2021-2030 in Taiwan and Vietnam. The collection amount in Taiwan is predicted to increase 2-fold until 2030 and the generation amount in Vietnam increases 6-fold. Moreover, different types of waste home appliances show distinct growth trends. The framework shows the capability to cope with nonlinear and uncertain characteristics and realize high accuracy. Based on the predictions, this paper quantifies the potential sustainability improvement given that realization of a well-established recovery system and a high recycling rate. The total revenue from recovery is estimated to reach 300 million in Taiwan by 2030, and 1.2 billion in Vietnam. Additionally, by 2030 the C O 2 e emissions in Taiwan are expected to reduce 0.7 million tons and in Vietnam will be reduction of 3.5 million tons. Socially, around 400-500 job vacancies can be created in Taiwan and more than 7000 jobs created in Vietnam in 2030 to achieve effective WEEE collection. The result facilitates the decision-making of the involved industries and regulators for better WEEE management and infrastructure investment. Besides, to have the collection trend in an advanced system (e.g., Taiwan) as a reference, it brightens the way to build and improve a formal collection system in a developing country or region (e.g., Vietnam).

Velocity planning serves as an important issue in motion planning for autonomous vehicles. The presented paper proposes a novel velocity planning method with minimum moving time on the basis of path curvature which is accomplished in three steps. First, the assigned path is divided into some elementary parts based on the path curvature. Second, the velocity planning is transformed into an unconstrained optimization problem by assuming the velocity of vehicle to be a specific cubic polynomial on every elementary part to avoid a sudden acceleration in path switching. Finally, we use a modified projection particle swarm optimization (PPSO) algorithm to obtain the time-optimal velocity profile . The proposed method can generate a smooth time-optimal velocity profile while considering all possible relevant constraints. Three examples are provided on different types of path to demonstrate that the final velocity profile is efficient to avoid the sudden acceleration change. Furthermore, the modified PPSO algorithm in this paper is used to solve the optimization problem with high dimensional variables when its upper bound is known, which can not be achieved by the general PPSO algorithm.

Bi-objective school bus scheduling optimization problem that is a subset of vehicle fleet scheduling problem is focused in this paper. In the literature, school bus routing and scheduling problem is proven to be an NP-Hard problem. The processed data supplied by our framework is utilized to search a near-optimum schedule with the aid of reinforcement learning by evolutionary algorithms. They are named as reinforcement learning-enabled genetic algorithm (RL-enabled GA), reinforcement learning-enabled particle swarm optimization algorithm (RL-enabled PSO), and reinforcement learning-enabled ant colony optimization algorithm (RL-enabled ACO). In this paper, the performance characterization of reinforcement learning-enabled evolutionary algorithms for integrated school bus routing and scheduling problem is investigated. The efficiency of the conventional algorithms is improved, and the near-optimal schedule is achieved significantly in a shorter duration with the active guidance of the reinforcement learning algorithm. We attempt to carry out extensive performance evaluation and conducted experiments on a geospatial dataset comprising road networks, trip trajectories of buses, and the address of students. The conventional and reinforcement learning integrated algorithms are improving the travel time of buses and the students. More than 50% saving by the conventional and the reinforcement learning-enabled ant colony optimization algorithm compared to the constructive heuristic algorithm is achieved from 92nd and 54th iterations, respectively. Similarly, the saving by the conventional and the reinforcement learning-enabled genetic algorithm is 41.34% at 500th iterations and more than 50% improvement from 281st iterations, respectively. Lastly, more than 10% saving by the conventional and the reinforcement learning-enabled particle swarm algorithm is achieved from 432nd and 28th iterations, respectively.

In order to meet the real-time and accurate requirements of multi-robot path planning in dynamic environment, this paper adopted wireless sensor network to locate robots and obstacles and used an improved artificial intelligent algorithm to plan path. In this paper, a jumping mechanism particle swarm optimization (JPSO) algorithm and a safety gap obstacle avoidance algorithm (SGOA) algorithm were proposed. Compared with canonical PSO algorithm, JPSO algorithm has three improvement strategies: Fitness value evaluation function, new learning sample and jumping strategy. The JPSO algorithm updates the particles with poor comprehensive quality by jumping and adjusts the inertia weight adaptively according to fitness value evaluation function. With the cooperation of new learning samples, the global searching ability and precision of the algorithm can be improved. SGOA algorithm is mainly aimed at the problem that robots with low priority are stuck in a long wait and cannot continue to walk when avoiding obstacles. By implementing the SGOA algorithm, a new collision-free safety path can be optimized for the robot with low priority. In order to verify JPSO and SGOA algorithm, a lot of experiments were done. JPSO algorithm was compared with two other improved PSO algorithms with 6 standard test functions. The path planning and obstacle avoidance experiments of six robots were realized using the JPSO and SGOA algorithm. The experimental results show that JPSO algorithm has higher accuracy and faster convergence speed than the other two improved PSO algorithms, and SGOA algorithm can solve the dynamic obstacle avoidance problem in the path planning of multiple robots well.

Blisk manufacturing generally involves two steps in electrochemical machining, namely roughing and finishing, with the aim of the former being to form the blade blank with an allowance that is as uniform as possible. This paper focuses on improving the allowance uniformity in the roughing stage of blisk. Electrochemical trepanning (ECTr) is an effective roughing method. To homogenize the allowance distribution of twisted blades on a blisk in ECTr, this paper proposes a cathode-rotating feeding strategy that involves both a constant rotation rate and a variable one. To examine how those two modes differ, kinematic simulations are performed. To determine the optimal rotation feeding trajectories, under the established parametric model, an evaluation criterion based on the minimum value among the maximum allowance differences (MADs) is proposed and adaptive particle swarm optimization intelligent algorithm is adopted. For a twisted blade with varying cross section, the feeding trajectories of the two modes are calculated and simulated. Under constant-rotation-rate feeding, the values of the MAD for the predicted blade are 1.478 mm and 1.432 mm at the concave and convex parts, respectively. The values of MAD are reduced to 0.849 mm and 0.961 mm, respectively, under variable-rotation-rate feeding, and the uniformities of the allowance distributions are improved by 42.6 % and 32.9 %, respectively. The experiment of cathode-rotating feeding ECTr with variable rotation rate was performed. For the machined blade, the values of MAD at the concave and convex parts are 0.955 mm and 0.786 mm, respectively. The deviations between the experiments and simulations are 11.1 % and 18.2 %, respectively, thereby showing the optimization method to be effective.

With the increasing proportion of renewable energy (mainly wind power and photovoltaic) connected to the grid, the fluctuation of renewable energy power brings great challenges to the safe and reliable operation of power grid. As a clean, low-carbon secondary energy, hydrogen energy is applied in renewable energy (mainly wind power and photovoltaic) grid-connected power smoothing, which opens up a new way of coupling hydrogen storage energy with renewable energy. This paper focuses on the optimization of capacity of electrolyzers and fuel cells and the analysis of system economy in the process of power output smoothing of wind/photovoltaic coupled hydrogen energy grid-connected system. Based on the complementary characteristics of particle swarm optimization (PSO) and chemical reaction optimization algorithm (CROA), a particle swarm optimization-chemical reaction optimization algorithm (PSO-CROA) are proposed. Aiming at maximizing system profit, the capacity of electrolyzers and fuel cells are constrained by wind power fluctuation, and considering environmental benefits, government subsidies and time value of funds, the objective function and its constraints are established. According to the simulation analysis, by comparing the calculated results with PSO and CROA, it shows that PSO-CROA effectively evaluates the economy of the system, and optimizes the optimal capacity of the electrolyzers and fuel cells. The conclusion of this paper is of great significance for the application of hydrogen energy storage in the evaluation of power smoothness and economy of renewable energy grid connection and the calculation of economic allocation of hydrogen energy storage capacity.

In order to reduce the ammonia concentration in the cattle house, it is necessary to accurately predict the ammonia concentration in real time. This paper proposes an improved particle swarm QPSO-RBF combined prediction method of ammonia concentration in cattle house based on KPCA nuclear principal component analysis. At first, the collected environmental data is normalized and denoised based on KPCA nuclear principal component analysis, and the non-linear kernel principal component information of the sample information is extracted through the contribution rate. And, the relevant parameters of the radial neural network RBF are optimized based on the improved particle swarm algorithm QPSO global search performance to improve the accuracy and robustness of prediction. The method is applied to the prediction of ammonia concentration in a cattle farm in Langzhong, and the experimental results show that the KPCA-QPSO-RBF ammonia combined prediction model proposed in this paper has higher credibility and accuracy compared with the other four prediction models. The ammonia concentration prediction method proposed in this paper can provide a theoretical basis for the precise environmental regulation of the cattle house.

Accurate modeling of the photovoltaic (PV) module is essential because of the comprehensive system installation in electrical power stations. The scientists have therefore suggested a photovoltaic single-diode model (SDM) for effective PV modelling. The SDM is a simple and non-linear model comprising five unknown parameters. This paper, therefore, presents a novel hybrid approach called particle swarm optimization (PSO) and grey wolf optimization (GWO), in order to extract unknown parameters, such as Isd, Ip, a, Rse, and Rsh from the SDM model. This paper also shows a new cost function based on the values of the datasheet instead of using extensive experiments. This paper, therefore, used standard test condition (STC) data to estimate two parameters by optimizing three remaining parameters by using PSOGWO algorithm. This proposed algorithm is applied to two commercial PV panels, namely KC200GT and SQ85, to find its parameters. Following this, the I-V curves of these PV modules were plotted under STC for five individual runs of the simulation. To prove the performance of the proposed PSOGWO algorithm, it is compared based on the statistical results with other algorithms, such as GWO and hybrid GWO-cuckoo search (GWOCS).

Surface roughness plays a major role in the manufacturing of mechanical components, an increase in wear and corrosion happen when the surface roughness value is high. To get a good surface finish many industries find it difficult in optimizing the correct parameters. In this paper a research work is carried out to find the optimal controllable parameters such as speed, feed and depth of cut influencing the surface roughness result. In machining, the surface roughness value is to be maintained as low as possible and it is attained by the value of optimal cutting parameters. So, in this paper with the application of RSM and PSO technique the optimal value of the cutting conditions for giving the minimum value of surface roughness is compared. The machining process taken for experiments is reaming in EN1A leaded material using TiAIN coated tool by vertical machining center. A total of 16 experiments were planned by the CCD method, on comparing the results of 16 experiments a regression model is developed to formulate the fitness function. Then PSO algorithm for the reaming process is developed to predict the surface roughness value for the reaming process and compared the same with experimental value and RSM predicted value. It is observed from this study that the PSO technique is capable of estimating the optimal cutting conditions than RSM that yield the minimum surface roughness value.

Optimal sensor allocation can substantially reduce the life cycle maintenance costs of engineering systems. Considerable effort has been exerted to model the causal relationship between sensors and faults, but without considering the propagation of fault risk. In this paper, a grey relational analysis (GRA) based quantitative causal diagram (QCD) sensor allocation strategy is proposed that can take account of the influence of the propagation of fault risk. QCD is used to describe both the fault-sensor causal relationship and the fault-to-fault causal relationship. A data-driven-based GRA is applied in QCD to calculate the coefficients of the propagation of fault risk. To achieve an accurate relationship between faults and sensors, an improved quantitative analytic hierarchy process is proposed to calculate the coefficients between faults and sensors that is defined as sensor detectability in this paper. An optimal sensor allocation strategy is then developed using an improved particle swarm optimization (IPSO) algorithm under the constraint on sensor detectability to minimize fault unobservability and total cost. The proposed strategy is demonstrated by a case study on a single-phase inverter system. Compared with two other sensor allocation strategies, the results show that the proposed strategy can obtain the lowest fault unobservability of per unit cost (−0.242) for sensor allocation under the propagation of fault risk.

Due to weather, seasons, and other factors, photovoltaic power generation cannot be predicted accurately. A Hybrid energy storage system can effectively reduce the impact of unbalanced power generated by this situation. In this paper, retired power batteries and super capacitors are used to form an energy storage system. A community system model is established. An improved lumped average empirical mode decomposition algorithm is used to decompose unbalanced power. Hilbert transform is used to obtain the reference boundary frequency of the energy storage system. Taking the minimum community investment cost as the objective function, a dimensional gravity center reverse mutation particle swarm optimization algorithm is used to solve the problem. The capacity allocation with good investment economy is determined. Two cases of conventional battery energy storage and retired power batteries are analyzed through numerical simulation. The results show that the hybrid energy storage system based on retired power batteries proposed in this paper can reduce investment and has a better economy.

In a continuous bistable system, when the input signal is continuously increased, the output signal tends to be stable and no longer increases. At this time, the weak signal under strong background noise is difficult to be extracted, which means saturation occurs. Aiming at the saturation characteristics of stochastic resonance (SR), the proposed piecewise nonlinear bistable system (PNBSR) model has achieved certain results. However, the potential barrier in the middle of the PNBSR method still completely uses the potential function of classical bistable stochastic resonance (CBSR). There is no fundamental solution to the fourth-order limitation. This paper explores an improved piecewise mixed stochastic resonance (PMSR) potential model. The fourth-order potential function that restricts particle motion in CBSR is improved to a piecewise second-order potential function. This potential function subverts the shape of the traditional potential function and presents a symmetrical double-hook shape. Based on PMSR model, this paper uses particle swarm optimization (PSO) to select system parameters and elaborates the characteristics of the potential function curve in detail. Under the same conditions, the output signal-to-noise ratio (SNR) curve of the improved system is generally higher than that of the CBSR and PNBSR systems. Experiments on bearings and gears show that the proposed method can accurately extract weak fault features, and the effect is better than the PNBSR method.

Resilient operation of medium/large scale off-grid energy systems requires continuous and sustainable energy resources. In this view, a nuclear-renewable integrated system could be a potential energy network. This paper proposes three methods, called Direct Coupling, Single Resource and Multiple products-based Coupling, and Multiple Resources and Multiple products-based Coupling, of hybridization for optimal planning of Nuclear-Renewable Micro Hybrid Energy System (N-R MHES). In N-R MHES, Micro Modular Reactor (MMR) is coupled with Renewable Energy Sources (RESs) to provide a reliable, resilient, and sustainable solution to energy crisis at remote locations. Complex mathematical modeling of N-R MHES, based on distinct proposed hybridization methods, is carried out in this paper. Particle Swarm Optimization (PSO) algorithm is used to achieve optimal system configuration and to assess the effectiveness and performability of different N-R MHESs. The objective of the optimization problem is to obtain the lowest Net Present Cost (NPC). The simulation results show that multiple resources and multiple products-based N-R MHES provides the lowest NPC ($ 98.3 million), compared to directly coupled N-R MHES ($ 165 million) and single resource and multiple products-based N-R MHES ($ 161.02 million), with an acceptable margin of reliability. System reliability is evaluated based on a technical Key Performance Indicator (KPI), named Loss of Power Supply Probability (LPSP). A sensitivity analysis has also been conducted to evaluate the impacts of different economic system parameters on NPC. This research explicitly focuses on the prospect of resilient N-R MHES for off-grid applications.

The prediction of short term power load owns a great influence on performance of the whole electric system. Raising the result of power load forecasting is always a research spot. This paper proposes a method combined Elman neural network (ENN) and the particle swarm optimization (PSO) for the short-term power load forecasting. Firstly, this paper introduces the principle of ENN and PSO algorithm respectively and analyzes performance of network influenced by parameters of ENN. Then the particle swarm optimization algorithm is applied to searching the optimal learning rate of ENN. To study the capability of the method proposed in this paper, the method is utilized for the short-term power load forecasting, which is suitable to be solved by ENN. Besides, a comparison experiment on this method (PSO–ENN) with general regression neural network (GRNN), the original ENN and the traditional back-propagation neural network (BPNN) is given out to illustrate effectiveness of PSO–ENN.

This paper introduces a Mixed Particle Swarm Optimization (MPSO) approach for active power loss minimization and voltage profile improvement in the distribution network. The developed technique joins the Binary Particle Swarm Optimization (BPSO) and the conventional PSO algorithms. The first one is devoted to identify the optimal distribution network configuration, while the second one is used to solve Distributed Generation (DG) placement and sizing problems. To evaluate the performance of the developed approach, three different load scenarios were assessed during network reconfiguration (NR) and DG integration. Simulations are conducted on two distribution test systems, namely, the IEEE-33-bus and the IEEE-69-bus. The obtained results clearly demonstrate the performance and the effectiveness of the proposed method to find optimal status of switches, as well as DG locations and sizes. A benchmark comparison is presented to prove the efficiency of the proposed MPSO with regard to other optimization techniques. The results show that MPSO outperforms these techniques in terms of quality of solution, power loss reduction and voltage profile enhancement. This study is an extension of the earlier published conference paper.

The field of neuroevolution has achieved much attention in recent years from both academia and industry. Numerous papers have reported its successful applications in different fields ranging from medical domain to autonomous systems. However, it is not clear which evolutionary optimization techniques lead to the best results. In this paper, multilayer perceptron (MLP) neural networks (NNs) are trained and optimized using four advanced bio-inspired evolutionary algorithms (EA). The algorithms are Multi-Verse Optimizer (MVO), Moth-flame optimization (MFO), Cuckoo Search (CS) and Particle Swarm Optimization (PSO). Each algorithm is equipped with two operators: evolutionary population dynamics and mutation, which impact on exploration and exploitation. Optimized MLPs are then used for the navigation of an autonomous robot. Accuracy and area under the curve metrics are used for the evaluation and comparison metrics. Moreover, two well-regarded gradient descent algorithms including Back propagation (BP) and Levenberg Marquardt (LM) are utilized to validate the results obtained by evolutionary-based MLP trainers. It is observed that MLPs developed using MFO are the most robust ones among MLPs trained using other evolutionary and gradient descent algorithms.

The solution of optimization problems with polymorphic uncertain data requires combining stochastic and non-stochastic approaches. The concept of uncertain a priori parameters and uncertain design parameters quantified by random variables and intervals is presented in this paper. Multiple runs of the nonlinear finite element model solving the structural mechanics with varying a priori and design parameters are needed to obtain a solution by means of iterative optimization algorithms (e.g. particle swarm optimization). The combination of interval analysis and Monte Carlo simulation is required for each design to be optimized. This can only be realized by substituting the nonlinear finite element model by numerically efficient surrogate models. In this paper, a multilevel strategy for neural network based surrogate modeling is presented. The deterministic finite element simulation, the stochastic analysis as well as the interval analysis are approximated by sequentially trained artificial neural networks. The approach is verified and applied to optimize the concrete cover of a reinforced concrete structure, taking the variability of material parameters and the structural load as well as construction imprecision into account.

The development and utilization of renewable energy sources can not only effectively reduce carbon dioxide emissions, but also provide access to electricity to more parts of the world. A standalone hybrid system based on renewable sources is a promising way to supply reliable and continuous power in remote areas to which the grid has not extended. This paper designs and investigates a photovoltaics (PV)-wind-hydropower station with pumped-storage installation (HSPSI) hybrid energy system in Xiaojin, Sichuan, China as case of study. HSPSI can use the available flow of the river and store surplus energy generated from wind and PV by pumping water from the lower reservoir to the upper one. From the perspective of the investors, the techno-economic index is usually used to design the PV-wind-HSPSI hybrid energy system which aims to find the optimal configure with maximum power supply reliability and minimum investment cost. The trade-off analysis between the two objectives is based on Pareto optimality theory by means of Multi-Objective Particle Swarm Optimization (MOPSO). Besides, this paper takes the curtailment rate (CR) of the wind and PV power into consideration due to policy requirements. The relationship between the two objectives under various CR are analyzed and compared. Several results can be obtained as follows: 1) Comparing with the PV-HSPSI and wind-HSPSI hybrid energy system, the levelized cost of energy (LCOE) of the PV-wind-HSPSI hybrid energy system can reduce by 32.8% and 45.0% respectively. 2) For the PV-wind-HSPSI hybrid energy system, the LCOE can be as low as 0.091 $/kWh when 5% LPSP can be acceptable. 3) The policy of CR is unfavorable for the investors which leads to a higher investment cost. 4) Particle Swarm Optimization (PSO) performs better than genetic algorithm (GA) and Simulated Annealing method (SA) with a least LCOE. 5) both MOPSO and weighted sum approach (WSA) have a good performance to find the Pareto fronts and its hypervolume indicator (HV) is calculated.

Cloud computing aimed at offering elastic resource allocation on demand to cloud consumers. Building a cloud resource demand prediction model is a challenging task because cloud consumer’s demand changes over time. Most of the current works in cloud resource demand prediction study the problem from the cloud provider perspective. In this paper, we study the problem from the cloud consumer perspective with the aim to help the consumers to meet their resource needs, derive estimates for the required IT budget, select the best cloud providers, and get better pricing through the advanced reservation of required cloud resources. We develop a new Swarm Intelligence Based Prediction Approach (SIBPA) to predict with higher accuracy the resource needs of a cloud consumer in terms of CPU, memory, and disk storage utilization. The SIBPA is also able to predict the response time and throughput which in turn enables the cloud consumers to make a better scaling decision. It also takes into account the dynamic behavior of consumer requests in a long term period and the seasonal or/and trend patterns in time series. The SIBPA uses the Particle Swarm Optimization (PSO) approach for selecting the best features from the dataset and for estimating the parameters of the prediction algorithms. The experimental results reveal that the prediction accuracy of the SIBPA outperforms the current prediction models. In terms of CPU utilization prediction, the accuracy of SIBPA outperforms the accuracy of the existing cloud consumer prediction frameworks that use Linear Regression, Neural Network, and Support Vector Machines approaches by 56.95%, 80.42%, and 63.86% respectively according to RMSE, and by 72.66%, 44.24%, and 56.78% according to MAPE. The accuracy of SIBPA also outperforms the accuracy of the existing cloud consumer prediction frameworks in terms of response time, throughput, and memory utilization predictions. The analysis and experiment results of SIBPA are discussed in detail in this paper.

In high dimensional problem spaces, particle swarm optimization (PSO) is prone to unwanted roaming behaviour due to initial velocity explosion. A particle swarm’s movement patterns are strongly influenced by the inertia weight and acceleration coefficients . This paper investigates whether the initial velocity explosion can be curbed by appropriate choice of the inertia weight and the acceleration coefficients, which restrict the standard deviation of particle positions. It is shown that roaming behaviour cannot be solved by reducing swarm variance directly, but that the relationship between the parameters must also be considered. Furthermore, the paper investigates different movement patterns that may be exhibited by the swarm. It is shown that optimal parameter configurations differ between low and high dimensional problems. Specifically, parameter configurations which produce very smooth particle trajectories and restrict the swarm’s movement range are advantageous in high dimensional spaces. These movement patterns correspond to high inertia weight and low acceleration coefficients (eg. w = 0.9694 , c 1 = c 2 = 0.099381 ). Swarms with smooth particle trajectories exhibited significantly less unwanted roaming behaviour than swarms with chaotic or oscillating particle trajectories.

Carbon fiber reinforced plastic (CFRP) is without doubt one of the broadly-used composite in these days as an outcome of its high strength to weight ratio, corrosion resistance and ease of transportation make them a useful material. The drilling operation is important process for the assembly of large size composite parts. Therefore, choose optimum parameter for the drilling is essential task for the improve drilling quality and reduced drilling defect. In the present paper, optimize drilling procedure used to be accomplished on vertical drilling computer numeric control machine. The parameters taken into consideration for the drilling according to literature review present are spindle speed, feed rate and helix angle of drilling tool. Helix angle of drilling tools assume because of very less work found on this parameter. The RSM (Response surface Methodology) regression equation is used for the mathematical modeling of method parameters in the drilling of CFRP composites. GA (Genetic Algorithm), SA (Simulated Annealing), and PSO (Particle Swarm Optimization) has use for optimizing parameters for reduce delamination in the drilling of CFRP composites. This paper suggests the best optimization procedure with in SA, GA, PSO for drilling of CFRP via comparison of outcome and conformation experiment. The ANOVA outcome showed that feed rate and helix angle of tools are the essential influential parameters that affect the drilling quality (de-lamination) within the drilling of CFRP composites.

Optimal power flow is a nonlinear optimization method to enhance the performance and flexibility of a power system. This paper explores the use of particle swarm optimization (PSO) algorithm as an artificial intelligence technique to solve a single objective function of the optimal power flow problem. The objective function is the minimization of the transmission power losses by keeping the equality and inequality constraints on their secure limits. To test the effectiveness of the proposed method, different scenarios of the Nordic 44 model include maximum import to Norway and maximum export from Norway to the other Nordic networks, as well as hourly load data variations are tested with MATLAB software. The Nordic 44 model is the test system that has been used to analyze stability and control problems that are relevant to the Nordic power network. The test results show the convergence and effectiveness of the proposed method to solve OPF problem compared to Genetic Algorithm (GA) as intelligent method and OPF by MATPOWER as the other classical method to test convergence and effectiveness of the proposed method to solve OPF problem under various load cases (heavy and light loading) of Nordic 44 test system. © 2020 by the authors. This is an open access article under the CC BY-NC-ND license.

In this paper, physiological signals were measured from five participants, each participating in two sessions of experiment with identical experimental procedure. A simulation platform, AutoCAMS (Automation-enhanced Cabin Air Management System), was used to simulate a complex task environment of human-machine shared process control. Fuzzy models were constructed to quantitatively predict the human operator performance based on three EEG input features. The incremental-PID-controlled particle swarm optimization (IPID-PSO) algorithm was utilized to optimize the parameters of fuzzy models. The IPID-PSO algorithm incorporated incremental-PID-controlled search strategy to speed up the convergence of standard PSO algorithm. The operator performance modeling results are given to show the effectiveness of the IPID-PSO-tuned fuzzy modeling approach proposed to momentary operator performance assessment problem under consideration.

The paper describes two main approaches of periodic control under variable frequency conditions: frequency adaptive multioscillatory control (FAMOSC) and fractional delay repetitive control (FDRC). The methods are applied in the control system of a grid-tie converter to increase the quality of phase currents in case of distorted grid voltages. The paper compares structures, performance and implementation of FAMOSC, FDRC and the conventional approach of repetitive and multioscillatory control. Performances of the control systems are illustrated with experiments on a laboratory test bench. The article describes tuning process of FDRC and FAMOSC with the usage of Particle Swarm Optimization algorithm. A detailed analyse and research of the techniques in terms of computational complexity is presented. Practical hints for implementation and resource optimization of both techniques on DSP are included. For FAMOSC a fast implementation of prewarping is proposed.

Accurate wind speed forecasting is important in power grid security, power system management, operation and market economics. However, most research has focused only on improving either accuracy or stability, with few studies addressing the two issues, simultaneously. Therefore, we proposed a novel combined model based on multi-objective particle swarm optimization, which is applied to optimize the key parameters of the echo state network. Most combined wind speed forecasting methods just use the combination theory to combine individual methods, this paper uses echo state network to combine the intermediate wind speed forecasting results of three artificial neural networks. Moreover, a new dataset division mechanism based on the moving window is applied in this paper. Firstly, the length of the input data is changed from 5 to 15 for 1-step, 2-step and 3-step wind speed forecasting, after that, the optimal length of the input vector can be got. And then we apply this optimal length of the input vector to another dataset for further verifying the proposed method. In order to verify the forecasting effectiveness of the proposed forecasting model, the 80/min wind speed data of M2 tower of the National Wind Power Technology Center of the United States were taken as an example. The experimental results indicate that the proposed algorithm is superior to the other ten comparative models in prediction accuracy and stability, and it also performs better than the combined model that we have proposed before.

This paper presents an investigation into the short-term versus long-term performance of various particle swarm optimization (PSO) control parameter configurations. While evidence suggests that the best PSO parameter values to employ are time-dependent, this paper provides an in-depth examination of a small set of parameter values to provide a more concrete quantification of the performance degradation observed with specific control parameter configurations over time. Given that the short-term performance is not necessarily indicative of long-term performance, this paper proposes that machine learning techniques be used to build predictive models based on two easily-observable landscape characteristics. Finally, using the predictive models as a basis, this paper also proposes a parameter-free PSO algorithm, which performs on par with other top-performing PSO variants, namely the three best performing static PSO configurations, particle swarm optimization with time-varying acceleration coefficients (PSO-TVAC), and particle swarm optimization with improved random constants (PSO-iRC).

To classify various sonar dataset, this paper proposes the use of the newly developed Whale Optimization Algorithm (WOA) algorithm for training Multi-Layer Perceptrons Neural Network (MLPs NN). Similar to other evolutionary classifiers, trapping in local minima, slow convergence rate, and non-real-time classification are three shortcomings it confronts in solving high-dimensional problems. Due to the novelty of WOA trainer, there is little in the literature regarding decreasing aforementioned deficiencies. In this paper, we also utilize seven spiral shapes to improve the performance of the WOA trainer. To assess the performance of the proposed classifiers, these networks will be evaluated using the three real-world practical sonar dataset. For endorsement, the results are compared to five popular meta-heuristics trainers include Particle Swarm Optimization (PSO), Gravitational Search Algorithm (GSA), Ant Colony Optimization (ACO), Gray Wolf Optimization (GWO), and WOA. The results show that new classifiers indicate better performance than the other benchmark algorithms, in terms of avoidance from getting stuck at local minima, classification accuracy, and convergence speed.

This paper studies the Solid Oxide Electrolyzer Cell as a promising system in the sustainable development for the hydrogen economy and energy systems as a robust system. The Solid Oxide Electrolyzer Cell converts the steam and carbon-dioxide directly to functional fuels through consumption of the additional electrical power of green power sources or off-peak network powers. The present paper evaluates the static efficiency of the SOEC under four various gas mixtures. Modeling of this system is performed using Elman neural network (ENN) and modified particle swarm optimization (MPSO) algorithm. The MPSO algorithm is utilized to determine the optimal values for ENN adjustable parameters. It's known from the empirical results that the steam and carbon-dioxide concentrations can affect the SOEC efficiency. The operational potential and volume share of the hydrogen, carbon dioxide and steam are considered as the system inputs, and efficiency (current) is remarked as its output. The correlation factors of the achieved model are greater than 0.999, and its MSE (mean squared error) is lower than 0.017. It reveals that the forecasted values are almost equal to the empirical data. Subsequently, the efficiency of the SOEC is studied using the achieved model of the MPSO-based ENN in various feedstock concentrations. Thus, this dataset that is used for ENN model can be desirable for different applications of fast-modeling in a standalone group. It as well can be useful for cost, computing-time, and computing burden reduction in a model construction in the efficiency analyzing and system-level designing processes.

International audience; In pickup and delivery problems, all the demands should be transported from pickup points (suppliers) to delivery points (customers) by vehicles while respecting a set of constraints. Honoring all demands is sometimes impossible when taking all the constraints into account. Therefore, the selective aspect is added to relax the constraint that all the demands should be satisfied. This paper studies a variant called the selective pickup and delivery problem with transfers (SPDPT). The transfers mean that some demands can be transferred from one vehicle to another one, which gives a chance to find more solutions. A mixed integer linear program is firstly proposed to describe the studied problem. Two objectives have been considered in the paper, maximizing the profit and minimizing the distance. The model is then validated on new generated instances. Due to the complexity of the problem, large instances could not be solved to optimality in a reasonable time. As an alternative, a new metaheuristic based on a hybrid particle swarm optimization is developed to tackle this bi-objective problem. The results show that this proposed method is efficient and competitive.

Nowadays all the world does its best to develop the power generation systems that depend on nature in order to reduce the dependence on fuel. Photovoltaic (PV) systems are considered one of the most important renewable energy resources. Scientific research has gained a high interest, especially in PV cell modeling and parameter estimation. The estimation of optimum parameters for the PV model has been considered the main target of the paper optimization problem. Equilibrium optimization (EO) algorithm is considered one of optimization algorithms inspired from nature physical phenomena. EO algorithm has been inspired from the nature physical process of controlling mass balance through specific volume until reaching equilibrium state. In this paper, an EO algorithm has been proposed and applied to prepare a mathematical model for photovoltaic solar cell. The challenge in this optimization problem is the non-linearity in PV solar cell characteristic. The EO algorithm has been evaluated through the following items. EO has been applied to estimate the parameters of different PV models such as single, double and triple PV models, which have different complexity. Applying the previous item for real PV application. The obtained results have been compared though different functions such as root mean square value and absolute mean error. In all cases, EO obtained results have been compared with the more recent optimization algorithms such as Particle swarm optimization (PSO), Teaching learn Based Optimization (TLBO) and Harries Hawk optimization (HHO). From the all obtained results, EO algorithm gives more accurate PV models in comparison with other optimization algorithms.

This paper deals with the comparison of models for predicting porosity and permeability of oil reservoirs by coupling a machine learning concept and petrophysical logs. Different machine learning methods including conventional artificial neural network, genetic algorithm, fuzzy decision tree, the imperialist competitive algorithm (ICA), particle swarm optimization (PSO), and a hybrid of those ones are employed to have a comprehensive comparison. The machine learning approach was constructed and tested via data samples recorded from northern Persian Gulf oil reservoirs. The results gained from the machine learning models used in this paper are compared to the relevant real petrophysical data and the outputs achieved by other methods employed in our previous studies. The average relative absolute deviation between the approach estimations and the relevant actual data is found to be less than 1% for the hybridized approaches. The results reported in this paper indicate that implication of hybridized machine learning methods in porosity and permeability estimations can lead to the construction of more reliable static reservoir models in simulation plans. Keywords: Machine learning, Neural network, Support vector machine, Porosity, Permeability, Well logs, Petro-physic

Traditionally, structural optimization is a numerical process; candidate designs are created and evaluated through numerical simulation (e.g., finite element analysis). However, when dealing with complex structures that are difficult to model numerically, large errors could exist between the numerical model and the physical structure. In this case, the optimization is less meaningful because the optimal results are associated with the numerical model instead of the physical structure. Experiments can be included in the optimization algorithm to represent complex structures or components. However, the time and cost limitations are prohibitive when iteratively constructing and evaluating complete structural systems. Real-time hybrid simulation (RTHS) is an efficient and cost-effective experimental tool that combines numerical simulation with experimental testing to capture the total structural performance. This paper proposes a framework for real-time hybrid optimization (RTHO); RTHS is used to evaluate the performance of candidate designs within the optimization process. The framework creates a cyber-physical optimization environment using RTHS, a modern experimental technique with roots in earthquake engineering. This paper outlines the framework for RTHO with accompanying proof-of-concept studies. In a preliminary study, the base isolation design of a two-story building was optimized for seismic protection. RTHO was further validated for the optimal selection of multiple semi-active control law parameters for an MR damper installed in the isolation layer of a five-story base-isolated building. Both cases used RTHS to evaluate the candidate designs and particle swarm optimization (PSO) to drive the optimization. RTHO is well-suited to evaluate nonlinear experimental substructures, in particular those that do not undergo permanent damage such as structural control devices. Structural damage, if of interest, can be modeled through the numerical component. This paper proposes and demonstrates the integration of state-of-the-art optimization algorithms with state-of-the-art experimental methods – a cyber-physical approach to structural optimization.

The time-varying nature of the heating loads of public buildings creates scope for exploring strategies to improve the energy system efficiency and to reduce the energy consumption and system operating costs. A well-researched and refined energy system operation strategy based on time-varying heating load demands is proposed in this paper. The proposed strategy is more effective and efficient than the existing experience-based operation strategies used to run energy systems. With full consideration of the factors affecting building heating loads under various scenarios, a multi-objective particle swarm optimisation algorithm combined with a scenario analysis is presented in this paper. The system efficiency and operation cost are set as two basic objectives to generate a Pareto frontier, and the occupant thermal comfort level is the dominant consideration while selecting an optimal state point for the final operation strategy. Using this simplified decision-making process, this approach can simultaneously calculate both the starting sequence and parameter settings for an optimised operation of the heat supply units. An energy plant on a university campus in Tianjin was selected to implement and evaluate this optimisation strategy. The case study results show that, without compromising the requirements of the thermal comfort of the building occupants, the energy system operating cost can be reduced by 38.9%, with an increase by a factor of 2.24 in the system coefficient of performance when compared with the current experience-based operation strategies.