Search

Intelligent fault diagnosis for wind energy systems requires identifying unique characteristics to differentiate various fault types effectively, even when data discrepancy occurs due to the unpredictable and dynamic nature of its environment. This article addresses some of the challenges of fault classification in wind energy systems by proposing an integrated approach that combines deep learning features with a resampled supervisory control and data acquisition (SCADA) dataset. The methodology involves resampling the imbalanced SCADA dataset using synthetic minority oversampling technique (SMOTE) and near‐miss undersampling techniques, extracting deep learning features using deep convolutional neural network, and feeding them into an XGBoost (extreme gradient boosting) classifier with tuned parameters using adaptive elite‐particle swarm optimization (AEPSO). The effectiveness of the proposed method is demonstrated through validation conducted on a different imbalanced dataset showing superior performance metrics in terms of accuracy. Additionally, the study contributes to methodological advancements in wind turbine fault diagnosis by providing a rigorous framework for fault classification. It is confirmed that utilizing the extracted deep learning features into the resampled data can significantly affect the classification performance metrics. Furthermore, the proposed integrated approach shows significance for fault diagnosis enhancement in wind energy systems and advancing the field towards more efficient and reliable operation. [ABSTRACT FROM AUTHOR]

This paper presents an Enhanced Particle Swarm Optimisation (EPSO) algorithm to improve multi-robot path planning by integrating a new path planning scheme with a cubic Bezier curve trajectory smoothing algorithm. Traditional PSO algorithms often result in suboptimal paths with numerous turns, necessitating frequent stops and higher energy consumption. The proposed EPSO algorithm addresses these issues by generating smoother paths that reduce the number of turns and enhance the efficiency of multi-robot systems. The proposed algorithm was evaluated through simulations in two scenarios, and its performance was compared against the basic PSO algorithm. The results demonstrated that EPSO consistently produced shorter, smoother paths with fewer directional changes, albeit with slightly longer execution times. This improvement translates to more efficient navigation, reduced energy consumption, and enhanced overall performance of multi-robot systems. The findings underscore the potential of EPSO in applications requiring precise and efficient path planning, highlighting its contribution to advancing the field of robotics. [ABSTRACT FROM AUTHOR]

One of the most important challenges in an autonomous and robotics system is the path planning in which the system finds the optimal path from start point to goal point. The traditional path planning algorithms may have large memory requirements which scale with the size and resolution of the configuration space. To address these challenges, this paper introduces a novel path planning algorithm that combines Particle Swarm Optimization and Artificial Potential Field in the form of a path planning algorithm for mobile robots. The biological and physical concepts from Particle Swarm Optimization and Artificial Potential Field algorithms are combined to yield an algorithm which minimizes instances of getting stuck in local minima and generates a smooth but feasible path. The developed method requires memory which scales only with the number of particles and the time taken to reach the goal. This results in a memory‐efficient solution that generates smooth and feasible paths for mobile robots navigating in a 2D space. [ABSTRACT FROM AUTHOR]

With the transition towards a low‐carbon energy system, renewable energy resources have been extensively developed. However, the limited ability of the power system to absorb renewable energy sources with high volatility, such as wind and solar power, has led to significant curtailment. Redundant electric energy can be converted into storable hydrogen energy through electrolysis and utilized for heating purposes. By leveraging the complementarity of diverse energy sources, optimal allocation of renewable energy can be achieved across a broader scope. However, in the current scheduling of multi‐energy systems, the efficiency of electrolyser is crudely assumed to be a constant, which results in scheduling solutions that deviate from the Pareto optimum. Therefore, a polymer electrolyte membrane electrolyser's model with non‐linear relationship between the load rate and conversion efficiency is proposed in this paper. To tackle the non‐convex optimal scheduling challenge, an adaptive chaos‐augmented particle swarm optimization algorithm is introduced, which effectively enhances computational efficiency while preventing entrapment in local optima. Case studies based on IEEE 14‐node system verified the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Recognising patterns and inferring nonlinearities between data that are seemingly random and stochastic in nature is one of the strong suites of machine learning models. Given a set of features, the ability to distinguish between useful features and seemingly useless features, and thereafter extract a subset of features that will result in the best prediction on data that are highly stochastic, remains an open issue. This study presents a model for feature selection by generating synthetic features and applying Binary Particle Swarm Optimisation with a Long Short-Term Memory-based model. The study analyses the correlation between data and makes use of Apple stock market data as a use case. Synthetic features are created from features that have weak/low correlation to the label and analysed how synthetic features that are descriptive of features can enhance the model's predictive capability. The results obtained show that by expanding the dataset to contain synthetic features before applying feature selection, the objective function was better optimised as compared to when no synthetic features were added. [ABSTRACT FROM AUTHOR]

This paper presents two novel bio-inspired particle swarm optimisation (PSO) variants, namely biased eavesdropping PSO (BEPSO) and altruistic heterogeneous PSO (AHPSO). These algorithms are inspired by types of group behaviour found in nature that have not previously been exploited in search algorithms. The primary search behaviour of the BEPSO algorithm is inspired by eavesdropping behaviour observed in nature coupled with a cognitive bias mechanism that enables particles to make decisions on cooperation. The second algorithm, AHPSO, conceptualises particles in the swarm as energy-driven agents with bio-inspired altruistic behaviour, which allows for the formation of lending–borrowing relationships. The mechanisms underlying these algorithms provide new approaches to maintaining swarm diversity, which contributes to the prevention of premature convergence. The new algorithms were tested on the 30, 50 and 100-dimensional CEC'13, CEC'14 and CEC'17 test suites and various constrained real-world optimisation problems, as well as against 13 well-known PSO variants, the CEC competition winner, differential evolution algorithm L-SHADE and the recent bio-inspired I-CPA metaheuristic. The experimental results show that both the BEPSO and AHPSO algorithms provide very competitive performance on the unconstrained test suites and the constrained real-world problems. On the CEC13 test suite, across all dimensions, both BEPSO and AHPSO performed statistically significantly better than 10 of the 15 comparator algorithms, while none of the remaining 5 algorithms performed significantly better than either BEPSO or AHPSO. On the CEC17 test suite, on the 50D and 100D problems, both BEPSO and AHPSO performed statistically significantly better than 11 of the 15 comparator algorithms, while none of the remaining 4 algorithms performed significantly better than either BEPSO or AHPSO. On the constrained problem set, in terms of mean rank across 30 runs on all problems, BEPSO was first, and AHPSO was third. [ABSTRACT FROM AUTHOR]

The electronic beam steering in conformal phased arrays is formed by exciting the multiple antennas with appropriate phase shifts. However, the malfunctioning of phase shifters connected to the central antenna elements in the conformal array distorts the radiation pattern of the array system severely as compared to edge elements resulting in the reduction of the array gain and increase in the side lobe levels. Here, the authors propose a non‐dominated sorting multi‐objective particle swarm optimisation (NS‐MOPSO) technique capable of recalculating the independent phases of working antenna elements in the array in such a manner as to correct the overall radiation pattern. To illustrate the radiation pattern's recovery capabilities of the optimisation technique in case of malfunctioning of any random phase shifter(s), a 1 x 7 microstrip patch antenna array operating at 2.45 GHz on a wedge‐shaped conformal structure was designed in CST simulator. To test, the radiation pattern's recovery capabilities of the NS‐MOPSO approach, phase shifters connected to the antenna elements in the array were made to malfunction. Then the optimisation algorithm recalculates the phases for individual antenna elements to achieve the desired corrected radiation pattern. The simulated and measured radiation pattern recovery results are in good agreement with each other. [ABSTRACT FROM AUTHOR]

Abstract Intelligent fault diagnosis for wind energy systems requires identifying unique characteristics to differentiate various fault types effectively, even when data discrepancy occurs due to the unpredictable and dynamic nature of its environment. This article addresses some of the challenges of fault classification in wind energy systems by proposing an integrated approach that combines deep learning features with a resampled supervisory control and data acquisition (SCADA) dataset. The methodology involves resampling the imbalanced SCADA dataset using synthetic minority oversampling technique (SMOTE) and near‐miss undersampling techniques, extracting deep learning features using deep convolutional neural network, and feeding them into an XGBoost (extreme gradient boosting) classifier with tuned parameters using adaptive elite‐particle swarm optimization (AEPSO). The effectiveness of the proposed method is demonstrated through validation conducted on a different imbalanced dataset showing superior performance metrics in terms of accuracy. Additionally, the study contributes to methodological advancements in wind turbine fault diagnosis by providing a rigorous framework for fault classification. It is confirmed that utilizing the extracted deep learning features into the resampled data can significantly affect the classification performance metrics. Furthermore, the proposed integrated approach shows significance for fault diagnosis enhancement in wind energy systems and advancing the field towards more efficient and reliable operation.

Abstract With the transition towards a low‐carbon energy system, renewable energy resources have been extensively developed. However, the limited ability of the power system to absorb renewable energy sources with high volatility, such as wind and solar power, has led to significant curtailment. Redundant electric energy can be converted into storable hydrogen energy through electrolysis and utilized for heating purposes. By leveraging the complementarity of diverse energy sources, optimal allocation of renewable energy can be achieved across a broader scope. However, in the current scheduling of multi‐energy systems, the efficiency of electrolyser is crudely assumed to be a constant, which results in scheduling solutions that deviate from the Pareto optimum. Therefore, a polymer electrolyte membrane electrolyser's model with non‐linear relationship between the load rate and conversion efficiency is proposed in this paper. To tackle the non‐convex optimal scheduling challenge, an adaptive chaos‐augmented particle swarm optimization algorithm is introduced, which effectively enhances computational efficiency while preventing entrapment in local optima. Case studies based on IEEE 14‐node system verified the effectiveness of the proposed method.

Abstract The electronic beam steering in conformal phased arrays is formed by exciting the multiple antennas with appropriate phase shifts. However, the malfunctioning of phase shifters connected to the central antenna elements in the conformal array distorts the radiation pattern of the array system severely as compared to edge elements resulting in the reduction of the array gain and increase in the side lobe levels. Here, the authors propose a non‐dominated sorting multi‐objective particle swarm optimisation (NS‐MOPSO) technique capable of recalculating the independent phases of working antenna elements in the array in such a manner as to correct the overall radiation pattern. To illustrate the radiation pattern's recovery capabilities of the optimisation technique in case of malfunctioning of any random phase shifter(s), a 1 x 7 microstrip patch antenna array operating at 2.45 GHz on a wedge‐shaped conformal structure was designed in CST simulator. To test, the radiation pattern's recovery capabilities of the NS‐MOPSO approach, phase shifters connected to the antenna elements in the array were made to malfunction. Then the optimisation algorithm recalculates the phases for individual antenna elements to achieve the desired corrected radiation pattern. The simulated and measured radiation pattern recovery results are in good agreement with each other.

This paper introduces a cooperative approach of a swarm intelligence algorithm and a linear programming solver to solve the capacitated facility location problem (CFLP). Given a set of potential locations to open facilities, the aim in CFLP is to find the minimum cost, which is the sum of facility opening costs and transportation costs. The developed solution strategy decomposes CFLP into two sub-problems. The former sub-problem has a binary domain. Although most of the swarm intelligence algorithms employ additional procedures such as sigmoid function to deal with binary domains, the proposed algorithm does not require for such methods. An adaptive mutation operator enhances this algorithm. The aim of the latter sub-problem is to generate a policy that optimally assigns customers to the opened facilities. In this regard, the generated binary vectors by the proposed algorithm are passed to a solver to optimise the generated linear model. Commonly used instances available in the literature are solved by the proposed strategy. Comprehensive experimental study includes comparisons with the sate-of-the-art. According to the statistically verified results, the proposed strategy is found as promising in solving CFLP. [ABSTRACT FROM AUTHOR]

Recognising patterns and inferring nonlinearities between data that are seemingly random and stochastic in nature is one of the strong suites of machine learning models. Given a set of features, the ability to distinguish between useful features and seemingly useless features, and thereafter extract a subset of features that will result in the best prediction on data that are highly stochastic, remains an open issue. This study presents a model for feature selection by generating synthetic features and applying Binary Particle Swarm Optimisation with a Long Short-Term Memory-based model. The study analyses the correlation between data and makes use of Apple stock market data as a use case. Synthetic features are created from features that have weak/low correlation to the label and analysed how synthetic features that are descriptive of features can enhance the model’s predictive capability. The results obtained show that by expanding the dataset to contain synthetic features before applying feature selection, the objective function was better optimised as compared to when no synthetic features were added.

Abstract This work implements the recently developed nth state Markovian jumping particle swarm optimisation (PSO) algorithm with local search (NS-MJPSOloc) awareness method to address the economic/environmental dispatch (EED) problem. The proposed approach, known as the Non-dominated Sorting Multi-objective PSO with Local Best (NS-MJPSOloc), aims to enhance the performance of the PSO algorithm in multi-objective optimisation problems. This is achieved by redefining the concept of best local candidates within the search space of multi-objective optimisation. The NS-MJPSOloc algorithm uses an evolutionary factor-based mechanism to identify the optimum compromise solution, a Markov chain state jumping technique to control the Pareto-optimal set size, and a neighbourhood’s topology (such as a ring or a star) to determine its size. Economic dispatch refers to the systematic allocation of available power resources in order to fulfill all relevant limitations and effectively meet the demand for electricity at the lowest possible operating cost. As a result of heightened public consciousness regarding environmental pollution and the implementation of clean air amendments, nations worldwide have compelled utilities to adapt their operational practises in order to comply with environmental regulations. The (NS-MJPSOloc) approach has been utilised for resolving the EED problem, including cost and emission objectives that are not commensurable. The findings illustrate the efficacy of the suggested (NS-MJPSOloc) approach in producing a collection of Pareto-optimal solutions that are evenly dispersed within a single iteration. The comparison of several approaches reveals the higher performance of the suggested (NS-MJPSOloc) in terms of the diversity of the Pareto-optimal solutions achieved. In addition, a measure of solution quality based on Pareto optimality has been incorporated. The findings validate the effectiveness of the proposed (NS-MJPSOloc) approach in addressing the multi-objective EED issue and generating a trade-off solution that is both optimal and of high quality. We observed that our approach can reduce $$\sim $$ ∼ 6.4% of fuel costs and $$\sim $$ ∼ 9.1% of computational time in comparison to the classical PSO technique. Furthermore, our method can reduce $$\sim $$ ∼ 9.4% of the emissions measured in tons per hour as compared to the PSO approach.

Over the past few decades, the scientific community's and industry's interest in additive manufacturing technologies has surged. This technology is distinguished by the layer-by-layer deposition of the raw materials and the piece's growth in a predetermined build orientation. This factor impacts the process' overall cost, surface quality, and other crucial parameters. Numerous methods to solve competing aspects have been proposed in the literature, with the more promising that iteratively uses ray-tracing techniques. Existing algorithms iterate for each discrete element of the model's bounding box projection onto the building platform. However, when optimisation algorithms are used on real-life industrial parts, computational time problems arise due to the high number of faces in the models. A new computational technique to determine the appropriate part orientation to reduce the support volume is proposed to address the problem. The method reduces the computational time, cycling the ray-tracing only on the triangles where the model surface is discretised. This approach has been integrated into an enhanced particle swarm optimisation algorithm to prove its efficiency. The approach is intended for industrial applications where it is necessary to handle complicated geometries quickly and efficiently to find the best orientation. Based on the computer's resources and the complexity of the faceted model, a set of case studies with an industrial engineering significance is used to demonstrate the approach's effectiveness. [ABSTRACT FROM AUTHOR]

Motivated by South Africa's need for the transition to a net-zero economy, this study investigates the integration of renewable energy sources (RESs) into oil refineries, considering the unique challenges and opportunities therein. The research focuses on optimising RES allocation using particle swarm optimisation (PSO), a data-driven approach that adapts to real-time operational conditions. Traditional energy management systems often struggle with the inherent variability of RESs, leading to suboptimal energy distribution and increased emissions. Therefore, this study proposes a PSO-based renewable energy allocation strategy specifically designed for oil refineries. It considers factors like the levelised cost of energy, geographical location, and available technology. The methodology involves formulating the optimisation problem, developing a PSO model, and implementing it in a simulated oil refinery environment. The results demonstrate significant convergence of the PSO algorithm, leading to an optimal configuration for integrating RESs and achieving cost reductions and sustainability goals. The optimisation result of ZAR 4,457,527.00 achieved through iterations is much better than the result of ZAR 4,829,638.88 acquired using linear programming as the baseline model. The mean cost, indicating consistent performance, has remained at its original value of ZAR 4,457,527.00, highlighting the convergence. The key findings include the average distance measurement decreasing from 4.2 to 3.4, indicating particle convergence; the swarm diameter decreasing from 4.7 to 3.8, showing swarm concentration on promising solutions; the average velocity decreasing from 7.8 to 4.25, demonstrating refined particle movement; and the optimum cost function achieved at ZAR 4,457,527 with zero standard deviation, highlighting stability and optimal solution identification. This research offers a valuable solution for oil refineries seeking to integrate RESs effectively, contributing to South Africa's transition to a sustainable energy future. [ABSTRACT FROM AUTHOR]

A set of non-linear optimisation algorithms are combined with a finite element simulation code to analyse the energy absorption and elastic stress wave propagation problem in multilayer/multimaterial armour systems under ballistic impacts. An Abaqus Python script is used to simulate the ballistic event and to generate the variables and post-processing outputs necessary for the integration with the optimisation algorithms. A number of modelling strategies are considered and three optimisation algorithms are used: Particle Swarm Optimisation (PSO), Genetic Algorithm (GA) and Simulated Annealing (SA). The performance and efficiency of each algorithm are assessed through four benchmark tests with different levels of complexity. A multi-objective optimisation procedure is proposed that uses the most efficient algorithm based on every single-objective formulation, variables and constraints from the benchmark tests, resulting in a highly non-linear problem. The proposed optimisation methods successfully achieve the study purposes both in the simulation of generic ballistic impacts and in the quality of the optimised solutions, demonstrating the potential for this type of optimisation method on terminal ballistic applications, serving as a standpoint for further studies into higher energy impacts and material non-linearities. [ABSTRACT FROM AUTHOR]

A four‐degree‐of‐freedom upper limb exoskeleton rehabilitation robot system with a gravity compensation device is constructed. The objective is to address the rehabilitation training needs of patients with upper limb motor dysfunction. A BP neural network adaptive control method based on particle swarm optimization is proposed. First, the degrees of freedom of the human body are analyzed, and a Lagrange method is employed to construct a dynamic model. Second, a particle swarm optimization back propagation neural network adaptive control algorithm based on particle swarm optimization is presented. Subsequently, the range of motion of the upper limbs is analyzed with reference to muscle anatomy and a three‐dimensional motion capture system. And the robot structure design is analyzed in detail. Finally, simulation experiments were conducted, and the results demonstrated that the proposed method exhibited high effectiveness and accuracy. [ABSTRACT FROM AUTHOR]

Pneumatic artificial muscles (PAMs) possess compliant properties desirable for certain applications such as prosthetics and robotic structures. However, this compliance along with their inherent nonlinear dynamics make them difficult to accurately model and as such accurately control under certain control architectures. Common approaches to this problem include measuring the actuator's physical properties and approximating a model based on these parameters or using deep learning methods to train a model with the actuator's behaviours. This paper introduces an optimisation-based modelling approach based on a particle swarm optimisation (PSO) algorithm using a mass–spring–damper approximation for the PAM, as well as a piecewise modelling method that accounts for nonlinear dynamics. The use of optimisation to estimate model parameters removes the need to measure physical properties, and the three-element approximation allows for fast model generation with low computational complexity and training data requirements. Through multiple tests comparing model behaviour with real PAM motion, the accuracy of these models is confirmed to be promising for future work. Dynamic nonlinearities are properly accounted for using the piecewise modelling method, including both hysteresis and disproportionate input/output relationship across the stroke length of the actuator. Compared with other PAM modelling techniques, this method has improved generation time, lower computational load requirements, and complexity and can be applied to actuators for which the phenomenological mass–spring–damper model is a good approximation. [ABSTRACT FROM AUTHOR]

Friction stir welding (FSW) is defined as a solid-state welding method that is required to be accurate, especially for its motion. This requirement can be satisfied by implementing an accurate controller. The aim of this research was to develop an accurate control system based on a fuzzy-proportional integral derivative (PID) controller for parallel manipulator FSW robots. In order to achieve a higher accuracy in motion control, the tuning optimisation process for a fuzzy-PID controller was conducted using a genetic algorithm (GA) and particle swarm optimisation (PSO). The optimisation algorithms were applied to simultaneously tune the fuzzy rules and output of the membership function from the fuzzy inference system (FIS). The PID controller was designed and tuned using a MATLAB® PID Tuner to obtain the desired response. It was then developed into a fuzzy-PID controller with Sugeno type-1 FIS with 2 inputs and 1 output. The tuning optimisation of the fuzzy-PID controller using GA and PSO was performed to achieve the global minimum integral absolute error (IAE) of the angular velocity. MATLAB® Simulink® was employed to test and simulate the controllers for three motors in the FSW robot model. The IAE values of the PID controller implemented for each motor were 0.03644, 0.04893, and 0.04893. The IAEs of the implemented fuzzy-PID-GA (output and rules) controller were 2.061, 2.048, and 2.048; of the implemented fuzzy-PID-GA (output) controller were 0.03768, 0.05059, and 0.05059; of the fuzzy-PID-PSO (output and rules) controller were 0.01886, 0.0253, and 0.02533; and of the fuzzy-PID-PSO (output) controller were 0.03767, 0.05059, and 0.05059. Therefore, the fuzzy-PID-PSO (output and rules) controller gave the most accurate results and outperformed the others. [ABSTRACT FROM AUTHOR]

This work implements the recently developed nth state Markovian jumping particle swarm optimisation (PSO) algorithm with local search (NS-MJPSOloc) awareness method to address the economic/environmental dispatch (EED) problem. The proposed approach, known as the Non-dominated Sorting Multi-objective PSO with Local Best (NS-MJPSOloc), aims to enhance the performance of the PSO algorithm in multi-objective optimisation problems. This is achieved by redefining the concept of best local candidates within the search space of multi-objective optimisation. The NS-MJPSOloc algorithm uses an evolutionary factor-based mechanism to identify the optimum compromise solution, a Markov chain state jumping technique to control the Pareto-optimal set size, and a neighbourhood's topology (such as a ring or a star) to determine its size. Economic dispatch refers to the systematic allocation of available power resources in order to fulfill all relevant limitations and effectively meet the demand for electricity at the lowest possible operating cost. As a result of heightened public consciousness regarding environmental pollution and the implementation of clean air amendments, nations worldwide have compelled utilities to adapt their operational practises in order to comply with environmental regulations. The (NS-MJPSOloc) approach has been utilised for resolving the EED problem, including cost and emission objectives that are not commensurable. The findings illustrate the efficacy of the suggested (NS-MJPSOloc) approach in producing a collection of Pareto-optimal solutions that are evenly dispersed within a single iteration. The comparison of several approaches reveals the higher performance of the suggested (NS-MJPSOloc) in terms of the diversity of the Pareto-optimal solutions achieved. In addition, a measure of solution quality based on Pareto optimality has been incorporated. The findings validate the effectiveness of the proposed (NS-MJPSOloc) approach in addressing the multi-objective EED issue and generating a trade-off solution that is both optimal and of high quality. We observed that our approach can reduce ∼ 6.4% of fuel costs and ∼ 9.1% of computational time in comparison to the classical PSO technique. Furthermore, our method can reduce ∼ 9.4% of the emissions measured in tons per hour as compared to the PSO approach. [ABSTRACT FROM AUTHOR]

Abstract One of the most important challenges in an autonomous and robotics system is the path planning in which the system finds the optimal path from start point to goal point. The traditional path planning algorithms may have large memory requirements which scale with the size and resolution of the configuration space. To address these challenges, this paper introduces a novel path planning algorithm that combines Particle Swarm Optimization and Artificial Potential Field in the form of a path planning algorithm for mobile robots. The biological and physical concepts from Particle Swarm Optimization and Artificial Potential Field algorithms are combined to yield an algorithm which minimizes instances of getting stuck in local minima and generates a smooth but feasible path. The developed method requires memory which scales only with the number of particles and the time taken to reach the goal. This results in a memory‐efficient solution that generates smooth and feasible paths for mobile robots navigating in a 2D space.

Current environmental issues and government requirements, together with pressure from the market and other stakeholders, emphasise the importance of partner selection in constructing and operating sustainable supply chains. Strategic items, which carry both high supply risk and high importance of purchase, are particularly important in sustainable supply chains. This paper presents an integrated decision-making model, which aims to solve the partner selection and order allocation problem for strategic items in sustainable supply chains. In the proposed model, weightings of different decision-makers are first calculated using Trapezoidal Fuzzy Numbers. Then, Taguchi loss function is used to evaluate the relative importance of potential partners, with the weighting results of criteria by Best-Worst Method. Finally, considering the weights of different potential partners, Particle Swarm Optimisation (PSO) is used to solve the multi-objective programming problem, and Technique of Order Preference Similarity to the Ideal Solution (TOPSIS) is applied to identify the most appropriate Pareto solution for sustainable partner selection and order allocation of strategic items. An illustrative application of the proposed model is undertaken in a leading Chinese LED lighting manufacturer to show its effectiveness and applicability. [ABSTRACT FROM AUTHOR]

Abstract In distribution networks, among the planning problems, optimal placement of medium voltage to low voltage (MV/LV) transformers is a vital and challenging issue. Electrical load uncertainty is an important factor that affects the result of this planning problem. This paper investigates optimal allocation of service transformers with respect to the load uncertainty modelled by information gap decision theory (IGDT). For this aim, the planning problem is solved in risk‐neutral (RN) and risk‐averse (RA) frameworks. In RN strategy, objective function is defined to minimize the cost of service transformers and low voltage feeders as well as the cost of power losses. On the other hand, in RA strategy, objective function is defined to maximize the radius of the uncertainty in such a way that any deviation of the uncertain parameter results in an objective function value that is not worse than the critical limit. The optimization problem is solved by crow search algorithm (CSA) and particle swarm optimization (PSO) and the results are compared. In mid‐term planning, with respect to the deviation factors of 0.05, 0.1, 0.15, 0.2, 0.25 and 0.3, optimal values of the uncertainty radius are 5.89%, 13.64%, 21.37%, 28.97%, 34.39% and 43.46%, respectively. In long‐term planning, with respect to the deviation factors of 0.05, 0.1, 0.15, 0.2, 0.25 and 0.3, optimal values of the uncertainty radius are 6.92%, 13.33%, 20.39%, 27.03%, 34% and 40.46%, respectively. Moreover, on average, CSA finds more promising results than PSO.

Abstract The supervisory control and data acquisition (SCADA) system is one of the key requirements for monitoring the power systems state. The power system state is estimated from the state estimation (SE) function, which uses the measurements results from different points. Inaccurate estimation may cause inefficient management of power systems and making decisions. Usually, the number of measurement units (MUs) is limited so the optimal location of MUs is very important in successful and accurate state estimation. The optimal placement of MUs gets more complicated when the actual state of the power system is uncertain due to the high penetration of renewable generation and load uncertainties. Considering the power system's actual state uncertainty and measurement units’ inherent error, this work presents a probabilistic model for the uncertainty of measuring based on the K‐medoids data clustering technique. Then the probabilistic optimal placement of MUs is solved by a binary particle swarm optimization (PSO) method. Considering the mentioned uncertainties makes the obtained solution robust against all the probable scenarios. The proposed technique is implemented on the IEEE 14‐bus test system and the results are discussed. Results show the effectiveness of the proposed method in improving the accuracy of power system state estimation.

Abstract To ensure the safe and stable operation of 5G base stations, it is essential to accurately predict their power load. However, current short‐term prediction methods are rarely applied rationally in pertinent circumstances to the features of base station power load over time. For high accuracy and generalization capabilities, this work proposes a hybrid approach that combines gated recurrent unit (GRU) with particle swarm optimization (PSO) and completes ensemble empirical mode decomposition with adaptive noise (CEEMDAN). The complex load is decomposed into multiple components to improve the fit of the neural network. To deal with the nonlinearity that constrains the modal aliasing and data noise, CEEMDAN is used to reconstruct the trend and noise sequences. The GRU network is utilized to improve the neural network fitness and obtain long‐term features. In addition, PSO is used to optimize the number of neurons and the learning rate of the GRU. Compared with existing neural network GRUs, the RMSE is reduced by 16.6, the mean absolute error is reduced by 11.97, and the coefficient of R2 is improved by 0.13, indicating that the model has a better fitting effect. The comparisons prove that the proposed model has better accuracy than the existing methods.

Abstract This research proposes a new comprehensive methodology aimed at optimally managing electric vehicle (EV) charging in an unbalanced distribution system with consideration of grid capacity and voltage quality constraints as well as the stochastic driving and charging behaviour of EV users. A data mining algorithm is designed to generate suitable spatial and temporal EV and charger input data for EV scheduling that is decomposed into two subproblems. The lower‐level subproblem identifies the maximum load at each node and time and the upper‐level subproblem allocates charging slots for each EV being charged. Both subproblems are solved by developed particle swarm optimisation (PSO) algorithms. The effectiveness and robustness of the algorithms have been thoroughly validated by conducting rigorous tests on a modified IEEE 37‐bus distribution system with different EV penetration scenarios. The test results have confirmed the algorithms' performance in accommodating the increasing load associated with EV charging and successfully improving the system performance by maximising the system load factor, minimising load unbalance, and reducing the system power loss. All operational constraints on node voltages, and distribution transformer and feeder capacities of the existing power distribution infrastructure are fully respected while maintaining high user satisfaction represented by the average state of charge (SoC) of all EVs.

With the progression of smart vehicles, i.e., connected autonomous vehicles (CAVs), and wireless technologies, there has been an increased need for substantial computational operations for tasks such as path planning, scene recognition, and vision-based object detection. Managing these intensive computational applications is concerned with significant energy consumption. Hence, for this article, a low-cost and sustainable solution using computational offloading and efficient resource allocation at edge devices within the Internet of Vehicles (IoV) framework has been utilised. To address the quality of service (QoS) among vehicles, a trade-off between energy consumption and computational time has been taken into consideration while deciding on the offloading process and resource allocation. The offloading process has been assigned at a minimum wireless resource block level to adapt to the beyond 5G (B5G) network. The novel approach of joint optimisation of computational resources and task offloading decisions uses the meta-heuristic particle swarm optimisation (PSO) algorithm and decision analysis (DA) to find the near-optimal solution. Subsequently, a comparison is made with other proposed algorithms, namely CTORA, CODO, and Heuristics, in terms of computational efficiency and latency. The performance analysis reveals that the numerical results outperform existing algorithms, demonstrating an 8% and a 5% increase in energy efficiency. [ABSTRACT FROM AUTHOR]

Control on the variable damping coefficients in the semi-active damper enhances ride comfort and vehicle stability. The semi-active electrohydraulic damper (SEH) presented in this study incorporates voice coil-based robust valve control to modify the damping coefficients. However, the position tracking accuracy of the voice coil actuator (VCA) gets negatively influenced by the nonlinearities such as load variations due to external disturbances, back emf, and dynamic damper characteristics. Therefore, to achieve excellent position control, a restart particle swarm optimisation with the Gompertz function (PSO-RG) is presented to obtain optimal tuning control gain for the proportional integral derivative controller. The PSO-RG algorithm applies Gompertz function-based particle coefficients and restarting technique. These techniques allow the PSO-RG to overcome the limitations of standard PSO, such as premature convergence and particle entrapment in local minima. The algorithm is tested in five selected benchmark functions for 10, 30 and 50 dimensions. The test data conveys that PSO-RG outperforms the standard PSO in mean, standard deviation, the best solution, and convergence speed. The transient response on identified and validated model of VCA demonstrated a 75.21% reduction in integral absolute error value than conventional PSO. The obtained maximum sensitivity and total variation values proved the robustness and smoothness of PSO-RG tuned PID control. Furthermore, the experimental analysis on the quarter car model shows that PSO-RG tuned PID precisely tracked the reference position with a 21.66% decrease in root mean square error to conventional PSO tuned PID. The CarSim co-simulation test results in the large van model indicate the need for precise VCA position control in enhancing ride comfort and improving the roll stability of the vehicle. [ABSTRACT FROM AUTHOR]

In distribution networks, among the planning problems, optimal placement of medium voltage to low voltage (MV/LV) transformers is a vital and challenging issue. Electrical load uncertainty is an important factor that affects the result of this planning problem. This paper investigates optimal allocation of service transformers with respect to the load uncertainty modelled by information gap decision theory (IGDT). For this aim, the planning problem is solved in risk‐neutral (RN) and risk‐averse (RA) frameworks. In RN strategy, objective function is defined to minimize the cost of service transformers and low voltage feeders as well as the cost of power losses. On the other hand, in RA strategy, objective function is defined to maximize the radius of the uncertainty in such a way that any deviation of the uncertain parameter results in an objective function value that is not worse than the critical limit. The optimization problem is solved by crow search algorithm (CSA) and particle swarm optimization (PSO) and the results are compared. In mid‐term planning, with respect to the deviation factors of 0.05, 0.1, 0.15, 0.2, 0.25 and 0.3, optimal values of the uncertainty radius are 5.89%, 13.64%, 21.37%, 28.97%, 34.39% and 43.46%, respectively. In long‐term planning, with respect to the deviation factors of 0.05, 0.1, 0.15, 0.2, 0.25 and 0.3, optimal values of the uncertainty radius are 6.92%, 13.33%, 20.39%, 27.03%, 34% and 40.46%, respectively. Moreover, on average, CSA finds more promising results than PSO. [ABSTRACT FROM AUTHOR]

The present study focusses on optimising a single supported excavation pit to achieve a more economical design using finite element analyses. Two methods for automating the derivation of the excavation pit's necessary embedment depth are presented, which involve either embedment depth reduction using additional calculation phases or adapting the entire model with renewed discretisation. The bending moments as well as the earth pressure distribution along the wall show good agreement, indicating that both methods are suitable for application. Subsequently, the feasibility of using optimisation algorithms (Particle Swarm Optimisation and Differential Evolution) for dimensioning the single supported excavation pit regarding stress analysis of the wall is investigated. Therefore, the embedment depth and the position of the strut are varied for five different sheet pile walls and three different strut profiles. The results demonstrate that both algorithms perform well, particularly with a higher number of calculation steps. After varying iteration steps and population size, the Differential Evolution approach shows better performance compared to Particle Swarm Optimisation by means of finding the optimal solution after a lower number of computational steps. [ABSTRACT FROM AUTHOR]

To ensure the safe and stable operation of 5G base stations, it is essential to accurately predict their power load. However, current short‐term prediction methods are rarely applied rationally in pertinent circumstances to the features of base station power load over time. For high accuracy and generalization capabilities, this work proposes a hybrid approach that combines gated recurrent unit (GRU) with particle swarm optimization (PSO) and completes ensemble empirical mode decomposition with adaptive noise (CEEMDAN). The complex load is decomposed into multiple components to improve the fit of the neural network. To deal with the nonlinearity that constrains the modal aliasing and data noise, CEEMDAN is used to reconstruct the trend and noise sequences. The GRU network is utilized to improve the neural network fitness and obtain long‐term features. In addition, PSO is used to optimize the number of neurons and the learning rate of the GRU. Compared with existing neural network GRUs, the RMSE is reduced by 16.6, the mean absolute error is reduced by 11.97, and the coefficient of R2 is improved by 0.13, indicating that the model has a better fitting effect. The comparisons prove that the proposed model has better accuracy than the existing methods. [ABSTRACT FROM AUTHOR]

The supervisory control and data acquisition (SCADA) system is one of the key requirements for monitoring the power systems state. The power system state is estimated from the state estimation (SE) function, which uses the measurements results from different points. Inaccurate estimation may cause inefficient management of power systems and making decisions. Usually, the number of measurement units (MUs) is limited so the optimal location of MUs is very important in successful and accurate state estimation. The optimal placement of MUs gets more complicated when the actual state of the power system is uncertain due to the high penetration of renewable generation and load uncertainties. Considering the power system's actual state uncertainty and measurement units' inherent error, this work presents a probabilistic model for the uncertainty of measuring based on the K‐medoids data clustering technique. Then the probabilistic optimal placement of MUs is solved by a binary particle swarm optimization (PSO) method. Considering the mentioned uncertainties makes the obtained solution robust against all the probable scenarios. The proposed technique is implemented on the IEEE 14‐bus test system and the results are discussed. Results show the effectiveness of the proposed method in improving the accuracy of power system state estimation. [ABSTRACT FROM AUTHOR]

This research tries to stabilise a three degree-of-freedom series-type double inverted pendulum system by employing an adaptive state feedback control approach optimised by a particle swarm optimisation (PSO) algorithm. To this end, the dynamical equations are derived via Lagrangian method and linearised by utilising approximation approaches. Then, the state feedback scheme is implemented to control the system states, that is, the angle and angular velocity of the first and second poles as well as the position and velocity of the cart. In order to timely regulate the control gains, the adaptation rules based on the gradient descent method and sliding surface relations are applied. The particle swarm optimisation algorithm is implemented to optimally tune the design parameters of the controller based on a proper objective function defined as summation of integrals of absolute values of the system errors. The time responses of the angles of the poles and the position of the cart clearly depict the feasibility and efficiency of the introduced control strategy to stabilise the system from different initial conditions to the final desired values. [ABSTRACT FROM AUTHOR]

The rapid enhancement in social media over the internet generates massive information in real-time scenarios, which has a striking impact on big data analysis. It resulted in the elevated usage of emotions and sentiments in social media. This paper proffers a proficient sentiment analysis technique in Twitter data. The Twitter database is preprocessed includes, stemming, tokenisation, number removal and stop word removal, etc. The preprocessed words are then passed into the HDFS (Hadoop Distributed File System) to reduce the repeated words and are eliminated using the MapReduce technique. The emoticons and the non-emoticons are extorted as features. The resulted features are ranked with their intended meaning. Then, the classification is performed utilising the DLMNN (Deep Learning Modified Neural Network). The experimental results were examined by using the output parameter such as Accuracy, Recall, Precision, F-Score and Execution Time with other conventional techniques such as ANN, SVM, K-Means and DCNN to show the greatest outcome of the proposed model. Evaluation result shows that DLMNN achieved the greatest performance in terms of precision (95.78%), Recall (95.84%), F-Score (95.87%) and Accuracy (91.65%) when compared with the existing models. [ABSTRACT FROM AUTHOR]

This research proposes a new comprehensive methodology aimed at optimally managing electric vehicle (EV) charging in an unbalanced distribution system with consideration of grid capacity and voltage quality constraints as well as the stochastic driving and charging behaviour of EV users. A data mining algorithm is designed to generate suitable spatial and temporal EV and charger input data for EV scheduling that is decomposed into two subproblems. The lower‐level subproblem identifies the maximum load at each node and time and the upper‐level subproblem allocates charging slots for each EV being charged. Both subproblems are solved by developed particle swarm optimisation (PSO) algorithms. The effectiveness and robustness of the algorithms have been thoroughly validated by conducting rigorous tests on a modified IEEE 37‐bus distribution system with different EV penetration scenarios. The test results have confirmed the algorithms' performance in accommodating the increasing load associated with EV charging and successfully improving the system performance by maximising the system load factor, minimising load unbalance, and reducing the system power loss. All operational constraints on node voltages, and distribution transformer and feeder capacities of the existing power distribution infrastructure are fully respected while maintaining high user satisfaction represented by the average state of charge (SoC) of all EVs. [ABSTRACT FROM AUTHOR]

Abstract The Circulatory System Based Optimisation (CSBO) stands as a nascent metaheuristic optimisation algorithm known for its proficiency in tackling global optimisation problems. The authors introduce the Multi‐strategy Enhanced CSBO (MECSBO), an algorithm designed for global optimisation and Reliability‐based Design Optimisation (RBDO). MECSBO integrates adaptive inertia weight, golden sine operator and chaos strategy to augment the convergence capacity and efficiency of the original CSBO. Furthermore, MECSBO‐based RBDO algorithm is presented to address RBDO problem. The comparative analysis utilising standard real‐world benchmark functions has been carried out to validate the effectiveness of the proposed MECSBO. Several RBDO problems, including three typical numerical examples and three engineering cases, are used to show abilities of the proposed MECSBO‐based RBDO algorithm. The results demonstrated that MECSBO is outperformed comparing to the state‐of‐the‐art algorithms in terms of accuracy, efficiency, and robustness in RBDO problems.

Integrated optimisation of production scheduling and distribution decision is necessary for reducing the whole cost of the supply chain in the make-to-order business environment. This paper studies a new integrated production scheduling and vehicle routing problem (IPSVRP) with inventory holding, delivery, and tardiness costs. The considered IPSVRP is modelled as a triple-objective optimisation problem, where the first objective aims to obtain the minimal total holding cost in the inventory, the second one attempts to achieve the minimal total travelling cost, and the third one tries to acquire the minimal total tardiness cost. To obtain a set of diverse non-dominated solutions in the Pareto-optimal front of the problem, we first derive several key structural properties used to provide necessary conditions for any solution to be Pareto-optimal through theoretical investigation. Based on the derived structural properties, a level-based multi-objective particle swarm optimizer (LMPSO) is subsequently designed. The performance of LMPSO is analysed by conducting a set of experiments, and its superiority is verified through comparing with other optimisation algorithms. Moreover, the convergence behaviour of LMPSO is also investigated, and the experimental results prove that it has the ability to achieve a set of non-dominated solutions proximity to the true Pareto front. [ABSTRACT FROM AUTHOR]

Abstract While wave energy is regarded as one of the prominent renewable energy resources to diversify global low‐carbon generation capacity, operational reliability is the main impediment to the wide deployment of the related technology. Current experience in wave energy systems demonstrates that operation and maintenance costs are dominant in their cost structure due to unplanned maintenance resulting in energy production loss. Accurate and high performance simulation forecasting tools are required to improve the efficiency and safety of wave converters. This paper proposes a new methodology for significant wave height forecasting. It is based on incorporating swarm decomposition (SWD) and multi‐strategy random weighted grey wolf optimizer (MsRwGWO) into a multi‐layer perceptron (MLP) forecasting model. This approach takes advantage of the SWD approach to generate more stable, stationary, and regular patterns of the original signal, while the MsRwGWO optimizes the MLP model parameters efficiently. As such, forecasting accuracy has improved. Real wave datasets from three buoys in the North Atlantic Sea are used to test and validate the forecasting performance of the proposed model. Furthermore, the performance is evaluated through a comparison analysis against deep‐learning based state‐of‐the‐art forecasting models. The results show that the proposed approach significantly enhances the model's accuracy.

Abstract This paper proposes a method based on scenario optimization and meta‐heuristic algorithm to optimize the power system stabilizers (PSSs) for enhancement of small‐signal stability (SSS) considering power system uncertainties such as photovoltaic generation, wind turbine generation, and load. The proposed method consists of two stages. In the first stage, the uncertainties are modeled using probability functions and scenarios are created based on them. These scenarios are then used to obtain a joint probability where the most likely probabilities are chosen for the second stage. The second stage utilizes these critical scenarios to formulate an optimization problem. The objective function of the optimization problem is to enhance system's small signal stability margin with PSS parameters as constraints. The proposed method is then solved using a new meta‐heuristic optimization algorithm known as Jelly Search Optimizer to obtain the optimized parameter of PSSs. The proposed method is tested on a two‐area and five‐area system, and the results show that the system SSS margin is improved for the majority of uncertainty situations. Moreover, the proposed method is around 1.6 times faster compared to the conventional probability method when tested in the modified two‐area system while 5.7 times faster when tested in the modified five‐area system.

This research article focused on optimising the parameter related to radial basis function (RBF) by solving the Fisher’s equation numerically. To obtain the numerical solutions, Particle Swarm Optimisation (PSO) algorithm is used along with radial basis functions (RBFs). PSO has been used by a number of researchers to obtain the optimised results in various scientific applications. In this work, using RBF-pseudospectral method, partial differential equations (PDEs) are transformed into a system of ordinary differential equations (ODEs) then are solved in MATLAB using the ODE solver. Two numerical examples are presented to demonstrate the effectiveness and accuracy of the proposed method by computingL∞, L2, and Lrms error norms with their order of convergence. Also, it can be demonstrated from the tables that the obtained results are in conformity with the results available in the literature.

This paper presents an Enhanced Particle Swarm Optimisation (EPSO) algorithm to improve multi-robot path planning by integrating a new path planning scheme with a cubic Bezier curve trajectory smoothing algorithm. Traditional PSO algorithms often result in suboptimal paths with numerous turns, necessitating frequent stops and higher energy consumption. The proposed EPSO algorithm addresses these issues by generating smoother paths that reduce the number of turns and enhance the efficiency of multi-robot systems. The proposed algorithm was evaluated through simulations in two scenarios, and its performance was compared against the basic PSO algorithm. The results demonstrated that EPSO consistently produced shorter, smoother paths with fewer directional changes, albeit with slightly longer execution times. This improvement translates to more efficient navigation, reduced energy consumption, and enhanced overall performance of multi-robot systems. The findings underscore the potential of EPSO in applications requiring precise and efficient path planning, highlighting its contribution to advancing the field of robotics.

This paper presents two novel bio-inspired particle swarm optimisation (PSO) variants, namely biased eavesdropping PSO (BEPSO) and altruistic heterogeneous PSO (AHPSO). These algorithms are inspired by types of group behaviour found in nature that have not previously been exploited in search algorithms. The primary search behaviour of the BEPSO algorithm is inspired by eavesdropping behaviour observed in nature coupled with a cognitive bias mechanism that enables particles to make decisions on cooperation. The second algorithm, AHPSO, conceptualises particles in the swarm as energy-driven agents with bio-inspired altruistic behaviour, which allows for the formation of lending–borrowing relationships. The mechanisms underlying these algorithms provide new approaches to maintaining swarm diversity, which contributes to the prevention of premature convergence. The new algorithms were tested on the 30, 50 and 100-dimensional CEC’13, CEC’14 and CEC’17 test suites and various constrained real-world optimisation problems, as well as against 13 well-known PSO variants, the CEC competition winner, differential evolution algorithm L-SHADE and the recent bio-inspired I-CPA metaheuristic. The experimental results show that both the BEPSO and AHPSO algorithms provide very competitive performance on the unconstrained test suites and the constrained real-world problems. On the CEC13 test suite, across all dimensions, both BEPSO and AHPSO performed statistically significantly better than 10 of the 15 comparator algorithms, while none of the remaining 5 algorithms performed significantly better than either BEPSO or AHPSO. On the CEC17 test suite, on the 50D and 100D problems, both BEPSO and AHPSO performed statistically significantly better than 11 of the 15 comparator algorithms, while none of the remaining 4 algorithms performed significantly better than either BEPSO or AHPSO. On the constrained problem set, in terms of mean rank across 30 runs on all problems, BEPSO was first, and AHPSO was third.

While wave energy is regarded as one of the prominent renewable energy resources to diversify global low‐carbon generation capacity, operational reliability is the main impediment to the wide deployment of the related technology. Current experience in wave energy systems demonstrates that operation and maintenance costs are dominant in their cost structure due to unplanned maintenance resulting in energy production loss. Accurate and high performance simulation forecasting tools are required to improve the efficiency and safety of wave converters. This paper proposes a new methodology for significant wave height forecasting. It is based on incorporating swarm decomposition (SWD) and multi‐strategy random weighted grey wolf optimizer (MsRwGWO) into a multi‐layer perceptron (MLP) forecasting model. This approach takes advantage of the SWD approach to generate more stable, stationary, and regular patterns of the original signal, while the MsRwGWO optimizes the MLP model parameters efficiently. As such, forecasting accuracy has improved. Real wave datasets from three buoys in the North Atlantic Sea are used to test and validate the forecasting performance of the proposed model. Furthermore, the performance is evaluated through a comparison analysis against deep‐learning based state‐of‐the‐art forecasting models. The results show that the proposed approach significantly enhances the model's accuracy. [ABSTRACT FROM AUTHOR]

To address significant disturbances, including sudden air flow variation, model uncertainty, and unavoidable measurement noises during aeroengine transient tests in the intake environmental pressure simulation system (IEPSS), a sliding mode active disturbance rejection controller (SMADRC) is designed. The sliding mode control in SMADRC can deal with unmatched disturbances that are beyond the capabilities of the extended state observer (ESO) in ADRC. And the particle swarm optimization (PSO) algorithm is introduced to tune and optimize the controller parameters to further enhance the performance. To validate the effectiveness of the proposed method, simulations are conducted on the IEPSS software platform. The simulation results clearly demonstrate PSO‐SMADRC can reduce the mean squared error by 60.9%, the input oscillation by 68.7%, and the maximum deviation by 53.9%, compared with LADRC originally applied in the IEPSS. [ABSTRACT FROM AUTHOR]

Microgrids can assist in managing power supply and demand, increase grid resilience to adverse weather, increase the deployment of zero-emission energy sources, utilise waste heat, and reduce energy wasted through transmission lines. To ensure that the full benefits of microgrid use are realised, hybrid renewable energy-based microgrids must operate at peak efficiency. To offer an optimal solution for managing microgrids with hybrid renewable energy sources (HRESs) while taking microgrid reserve margins into account, the particle swarm optimisation (PSO) method is suggested. The suggested approach demonstrated good performance in terms of charging and discharging BESS and maintaining the necessary reserve margins to supply critical loads if the grid and renewable energy sources are unavailable. On a clear day, the amount of electricity sold to the grid increased by 58%, while on a partially overcast day, it increased by 153%. Microgrids provide a good return on investment for their operators when they are run at peak efficiency. This is because the BESS is largely charged during off-peak hours or with excess renewable energy, and power is only purchased during less expensive off-peak hours. [ABSTRACT FROM AUTHOR]