Metaheuristic Techniques Research Articles

Electrical and thermal performance analysis of hybrid photovoltaic/thermal water collector using meta-heuristic optimization

The photovoltaic/thermal (PV/T) flat-panel technology has numerous advantages over PV modules and separately mounted solar thermal collectors regarding overall effectiveness and space-saving. Hybrid PV/T solar collectors’ thermal and electrical performance is influenced by design parameters like mass flow rate, tube diameter, tube spacing, packing factor, and absorber conductivity. This paper focused on using several meta-heuristic optimization techniques, incorporating the following: multiverse algorithm, dragonfly algorithm, sine–cosine algorithm, moth-flame algorithm, whale algorithm, particle swarm algorithm, ant-lion algorithm, grey wolf algorithm, and particle swarm optimization algorithm in PV/T collector optimal design according to maximum total efficiency obtained. The outcomes of the various algorithms revealed that the maximum electrical efficiency of the PV/T collector ranged from 13.85 to 14.28%, while the maximum thermal efficiencies ranged from 41.41 to 52.08% under standard test conditions (1000 W/m2 and 25 °C). The optimized values for the design parameters of the PV/T collector were as follows: the absorber conductivity was determined to be 356.6 W/m K, the packing factor was optimized to 0.7, the mass flow rate was set at 0.019 kg/s, the tube width was determined to be 0.035 m, and the tube spacing was optimized to 0.0524 m. The results indicated that the grey wolf optimizer (GWO) algorithm proved to be highly effective in optimizing the design parameters of PV/T collectors. Furthermore, the study examined the relationship between the temperature of PV modules and PV/T collectors by considering variations in mass flow rate, packing factor, and tube width at different solar radiation levels. The results confirmed that the PV/T collector temperature exhibited improvements compared to the PV module temperature. As a result, this led to higher electrical efficiency and an overall increase in the total efficiency of the PV/T collector.

Novel rockburst prediction criterion with enhanced explainability employing CatBoost and nature-inspired metaheuristic technique

Rockburst is a major challenge to hard rock engineering at great depth. Accurate and timely assessment of rockburst risk can avoid unnecessary casualties and property losses. Despite the existence of various methods for rockburst assessment, there remains an urgent need for a comprehensive and reliable criterion that is easy to both apply and interpret. Developing a new rockburst criterion based on simple parameters can potentially fill this gap. With its advantages, this criterion can facilitate a more effective and efficient prediction of rockburst potential, thereby contributing significantly to enhancing safety measures. In this paper, combined with the internal and external factors of rockburst, four control variables (i.e., integrity index, stress index, brittleness index, and elastic energy index) were selected to be incorporated into a comprehensive rockburstability index (RBSI). Based on 116 sets of rockburst cases, the rockburst potential was accurately quantified and predicted using the categorical boosting (CatBoost) model and the nature-inspired metaheuristic African vultures optimization algorithm (AVOA). In its performance validation, the criterion achieved the highest accuracy of 90.48%, verifying the reliability and effectiveness of the proposed RBSI criterion. Additionally, an interpretive method was applied to analyze the variable influence on the criterion, facilitating the explanation of predictions and the analysis of the formula’s robustness under different conditions. In general, compared with existing criterion methods involving relevant indicators, the newly proposed RBSI criterion enhances the accuracy of rockburst potential prediction, and it can effectively and swiftly evaluate the preliminary risk of rockburst. Lastly, a graphical user interface was developed to provide a clear visualization of the assessment of rockburst potential.

A Bilevel Optimization Approach for Tuning a Neuro-Fuzzy Controller

This work presents a methodology to solve optimization problems with dynamic-size solution vectors containing continuous and integer variables. It is achieved by reformulating the original problem through a bilevel optimization approach and implementing metaheuristic techniques to solve it. In the selected case study, the optimization problem corresponds to tuning a neuro-fuzzy controller (NFC) that operates in a biodiesel production system for controlling temperature. The NFC performs well and is especially robust to disturbances, but due to its complexity, it is difficult to determine the best set of parameters for its use. This has led to biased searches based on criteria such as the experiences of designers. With the proposed method, it was possible to obtain a tuning that—when implemented in a simulation—led to results that surpassed those documented in the literature. Finally, the proposal offers flexibility for implementation with other controllers that have similar architectures and can be integrated into various other plants or processes.

Integrated transmission expansion planning incorporating fault current limiting devices and thyristor-controlled series compensation using meta-heuristic optimization techniques

Transmission expansion planning (TEP) is a vital process of ensuring power systems' reliable and efficient operation. The optimization of TEP is a complex challenge, necessitating the application of mathematical programming techniques and meta-heuristics. However, selecting the right optimization algorithm is crucial, as each algorithm has its strengths and limitations. Therefore, testing new optimization algorithms is essential to enhance the toolbox of methods. This paper presents a comprehensive study on the application of ten recent meta-heuristic algorithms for solving the TEP problem across three distinct power networks varying in scale. The ten meta-heuristic algorithms considered in this study include Sinh Cosh Optimizer, Walrus Optimizer, Snow Geese Algorithm, Triangulation Topology Aggregation Optimizer, Electric Eel Foraging Optimization, Kepler Optimization Algorithm (KOA), Dung Beetle Optimizer, Sea-Horse Optimizer, Special Relativity Search, and White Shark Optimizer (WSO). Three TEP models incorporating fault current limiters and thyristor-controlled series compensation devices are utilized to evaluate the performance of the meta-heuristic algorithms, each representing a different scale and complexity level. Factors such as convergence speed, solution quality, and scalability are considered in evaluating the algorithms’ performance. The results demonstrated that KOA achieved the best performance across all tested systems in terms of solution quality. KOA’s average value was 6.8% lower than the second-best algorithm in some case studies. Additionally, the results indicated that WSO required approximately 2–3 times less time than the other algorithms. However, despite WSO’s rapid convergence, its average solution value was comparatively higher than that of some other algorithms. In TEP, prioritizing solution quality is paramount over algorithm speed.

A mutation hill climber for thinning of concentric circular antenna arrays

ABSTRACT Thinned concentric circular antenna arrays (CCAAs) are crucial in modern wireless communication systems. CCAAs are widely used for efficient communication, directivity, and beamforming capabilities. Nevertheless, CCAAs encounter a challenge of radiation patterns characterised by high sidelobe levels (SLL). Designing thinned CCAAs to surmount this limitation for optimal performance can be complex and challenging. This paper employs a mutation hill climber (MHC) algorithm to optimise the CCAA structure. The goal is to attain an optimal design that balances the number of switched-on elements and reduces the maximum SLL. The performance and efficacy of the MHC are examined using two different cases of thinned CCAA design: two-ring and ten-ring configurations. Simulation results reveal the superiority of the MHC over the latest binary metaheuristic techniques in achieving the lowest maximum SLL and the number of switched-on elements. For the two-ring thinned CCAA, the MHC effectively switched off 50 antenna elements, reducing the maximum SLL by 24.92 dB. Meanwhile, for the ten-ring thinned CCAA, the MHC reduced the number of switched-on antenna elements from 440 to 184, reducing the maximum SLL by 34.09 dB.

Optimizing photovoltaic systems performance under partial shading using an advanced cuckoo search algorithm

Partial shading negatively impacts power output in photovoltaic systems (PVs), causing multiple local maximum power points (LMPP) instead of a single global maximum power point (GMPP). The cuckoo search (CS) technique utilizes the maximum power point tracking (MPPT) technique to extract the global maximum power (GMP) from shaded PVs. CS is a metaheuristic technique that has gained widespread recognition. Moreover, the CS algorithm is associated with several challenges, including a failure rate, long response time, and noticeable oscillations during steady-state operation. To address these limitations, our proposed advanced cuckoo search (ACS) algorithm is designed to overcome the shortcomings of the standard CS algorithm. The algorithm iteratively evaluates individual solar panels and collectively explores the solution space using levy flight operations. Persistent variables are used to store and track the current state and previous iterations. Where the duty cycles of the solar panels are optimally set to enhance the overall power generation efficiency. We also evaluate and analyze the results obtained from the performance of our proposed technique and compare them to the performance of the four most recent CS optimization techniques. for all test cases, the tracking efficiency was improved to 99.98% with a fast-settling time of <44 ms.

A hybrid PSO-GWO-based phase shift design for a hybrid-RIS-aided heterogeneous network system

The effectiveness of developing reconfigurable intelligent surfaces (RIS) for heterogeneous network (HetNet) systems has resulted in significant spectral efficiency (SE) gains. The majority of current research has not addressed effectively whether a hybrid metaheuristic technique may be used to create the hybrid RIS phase changes in HetNet. In this paper, we study a heterogeneous network (HetNet) assisted by a hybrid reconfigurable intelligent surface (H-RIS). Compared with the passive RIS, a hybrid RIS that has only 8% active elements is proposed to enhance by reflecting and amplifying incident signals. Hybrid RIS phase shift and SBS transmit beamforming are optimised. At the SBS, transmit beamforming based on zero-forcing is employed, whereas for hybrid RIS phase shift optimisation, the hybrid PSO-GWO (HPSOGWO) method is employed. The exploitation power of particle swarm optimisation (PSO) and the exploration power of the grey wolf optimizer (GWO) are combined in this hybrid approach. Simulation findings show that the suggested method, which uses only modest active RIS elements, can achieve a significant spectral efficiency improvement over both RIS-aided HetNet with totally passive RIS elements but with the SDR method to optimise the RIS phase changes and RIS-aided HetNet with entirely active RIS elements but with the Lagrange multiplier (LM) scheme to design the phase shift at the active RIS.

Model development and parameter calibration of a combined-cycle power generation unit via metaheuristic optimization techniques

Mathematical modeling of combined-cycle units has produced a variety of valuable results, primarily significant advances in their energy efficiency and education of power plant operators. These positive results motivate the need for more complex modeling and simulation techniques with the goal of greater accuracy and accessibility. This study presents a simplified and enhanced version of a gas turbine model for dynamic performance simulation. The theoretical improvements have been proved through modeling philosophy and simulation accuracy attained by metaheuristic optimization techniques. The model has been constructed using thermodynamic and mathematical concepts, with parameter optimization and calibration performed using metaheuristic optimizers. The suggested model’s resilience has been demonstrated by simulation results.

Applying the Sine-Cosine Optimization Algorithm to the Parametric Estimation Problem in Three-Phase Induction Motors

The steady-state analysis of electrical machines requires a detailed characterization of their equivalent electrical circuit, which adequately represents the transformation and interaction between electrical and mechanical energy. This research aims to characterize the equivalent circuit of three-phase induction motors by minimizing the mean square error between the measured and calculated torque variables. These torques are obtained from data provided by the manufacturer, including starting, peak, and full-load torques. A metaheuristic optimization technique is applied to solve the resulting nonlinear programming model based on the interactions between the sine and cosine functions. The numerical results obtained with this algorithm demonstrate its efficiency in terms of response quality, reaching objective function values of less than \(1\times10^{-8}\) with regard to the measured and calculated variables. Simulation results in two test systems allow concluding that the parametric estimation problem in three-phase induction motors is a multimodal optimization problem. This implies a potentially infinite set of solutions that minimize the root mean square error and adequately represent the behavior of the motor's output torque under various probable operating conditions.

Optimal power dispatch in hybrid power system for medium- and large-scale practical power systems using self-adaptive bonobo optimizer algorithm

Incorporating renewable energy sources (RESs) introduces a notable amount of uncertainty in the optimal planning and operation of electrical power grids. Under these circumstances, this paper proposes the application of a recently introduced metaheuristic optimization technique to solve the stochastic optimal power flow (OPF) problem involving wind and solar power sources. The self-adaptive bonobo optimizer (SaBO) is used to minimize three distinct objective functions: (i) Total generation cost (TGC) minimization, including both thermal and wind/solar generation costs, (ii) Power loss minimization, (iii) Combined generation cost and emissions effect minimization. The costs associated with the stochastic generation of wind and solar power included direct costs, reserves and penalty costs from the overestimation and underestimation of available wind and solar power, respectively. The performance of the proposed algorithm is evaluated on two power systems: the modified IEEE 30-bus and the Algerian DZA 114-bus test systems. To demonstrate the efficacy of the SaBO, the obtained results have been compared with those obtained from the Kepler optimization algorithm (KOA) and other recently published optimizers under the same case studies and constraints. The comparative results clearly show the superiority of the SaBO algorithm over all other well-known optimization algorithms provided in the literature for solving the OPF problem. This is evidenced by minimizing total generation costs of 781.2363 $/h for the modified IEEE 30-bus and 16,706.1630 $/h for the Algerian DZA-114-bus system. Furthermore, the integration of RES led to a notable 2.33% and 11.67% reduction in total generation cost for the IEEE 30-bus and Algerian DZA 114-bus systems, respectively, compared to their initial configurations without RESs. The promising findings highlight the powerful of the optimizer to solve non-linear and complex optimization problems in power systems.

A hybrid artificial intelligence approach for modeling the carbonation depth of sustainable concrete containing fly ash

One of the major challenges in the civil engineering sector is the durability of reinforced concrete structures against carbonation during the physico-chemical process of interaction of hydrated cementitious composites with carbon dioxide. This aggressive process causes carbon penetration into the reinforcement part, which affects the behavior of the structure during its lifetime due to corrosion risk. A countermeasure is using alternative cementitious materials to improve concrete texture and resist increased carbonation depth (CD). Considering that the CD test requires a long time and a skilled technician, this study strives to provide an alternative approach by moving from traditional laboratory-based methods towards artificial intelligence (AI) techniques for modeling the CD of sustainable concrete containing fly ash (CCFA). Despite the development of single AI models so far, it is undeniable that utilizing metaheuristic optimization techniques in the form of hybrid models can improve their performance. To this end, a new hybrid model from the integration of biogeography-based optimization (BBO) technique with artificial neural network (ANN) is developed for the first time to estimate the CD of CCFA. The error distribution results revealed that 59% of the ANN predictions had errors within the range of (− 1 mm, 1 mm], while the corresponding percentage for the ANN-BBO predictions was 70%, indicating an 11% reduction in the prediction errors by the proposed hybrid model. Furthermore, A10-index highlighted a performance improvement of 78% for the hybrid model, which met the closeness of the predicted values to the observed ones, so that the value of this index for models of ANN and ANN-BBO was 0.5019 and 0.8947, respectively. Analyzing the cross-validation confirmed the reliability and generalizability of the developed model. Also, the three most influential variables in estimating the CD were exposure time (27%), carbon dioxide concentration (22%), and water/binder (18%), respectively. Finally, the superiority of the ANN-BBO model was verified by comparing it with previous studies’ models.

Greater cane rat algorithm (GCRA): A nature-inspired metaheuristic for optimization problems

This paper introduces a new metaheuristic technique known as the Greater Cane Rat Algorithm (GCRA) for addressing optimization problems. The optimization process of GCRA is inspired by the intelligent foraging behaviors of greater cane rats during and off mating season. Being highly nocturnal, they are intelligible enough to leave trails as they forage through reeds and grass. Such trails would subsequently lead to food and water sources and shelter. The exploration phase is achieved when they leave the different shelters scattered around their territory to forage and leave trails. It is presumed that the alpha male maintains knowledge about these routes, and as a result, other rats modify their location according to this information. Also, the males are aware of the breeding season and separate themselves from the group. The assumption is that once the group is separated during this season, the foraging activities are concentrated within areas of abundant food sources, which aids the exploitation. Hence, the smart foraging paths and behaviors during the mating season are mathematically represented to realize the design of the GCR algorithm and carry out the optimization tasks. The performance of GCRA is tested using twenty-two classical benchmark functions, ten CEC 2020 complex functions, and the CEC 2011 real-world continuous benchmark problems. To further test the performance of the proposed algorithm, six classic problems in the engineering domain were used. Furthermore, a thorough analysis of computational and convergence results is presented to shed light on the efficacy and stability levels of GCRA. The statistical significance of the results is compared with ten state-of-the-art algorithms using Friedman's and Wilcoxon's signed rank tests. These findings show that GCRA produced optimal or nearly optimal solutions and evaded the trap of local minima, distinguishing it from the rival optimization algorithms employed to tackle similar problems. The GCRA optimizer source code is publicly available at: https://www.mathworks.com/matlabcentral/fileexchange/165241-greater-cane-rat-algorithm-gcra.

Optimal Allocation of Capacitor Banks and Distributed Generation: A Comparison of Recently Developed Metaheuristic Optimization Techniques on the Real Distribution Networks of ALG-AB-Hassi Sida, Algeria

Recent advancements in renewable energy technologies, alongside changes in utility infrastructure and progressive government policies, have bolstered the integration of renewable-based distributed generation units within distribution systems. This paper introduces the Energy Valley Optimizer, a novel tool designed for the strategic placement of distributed generation units and capacitor banks. This placement is crucial not only for optimizing energy loss and enhancing bus voltage stability but also for promoting sustainable energy use and reducing environmental impact over the long term. By minimizing energy loss and voltage fluctuations, the optimizer contributes to a more sustainable and resilient energy system. It achieves this through the optimal allocation of resources across various load patterns within a 24 h period and is tested on the ALG-AB-Hassi-Sida 157-bus distribution network in South Algeria. Comparative analysis with existing algorithms—such as the Liver Cancer Algorithm, Walrus Optimization Algorithm, and Zebra Optimization Algorithm—demonstrates the superior performance of the Energy Valley Optimizer. It not only enhances technical and economic efficiencies but also significantly lowers the total cost of energy over 24 years, thus supporting sustainable development goals in energy management.

Offline learning-based competitive swarm optimizer for non-linear fixed-charge transportation problems

The fixed-charge transportation (FCT) problem, an extension of the classical transportation problem, holds significance in practical logistics scenarios where fixed charges play a crucial role. Fixed charges categorize it as an NP-hard problem, posing challenges for conventional methods due to their inefficiency, high computational costs, and susceptibility to local optima. This paper introduces an enhanced evolutionary algorithm, offline learning-based competitive swarm optimization (OLCSO), tailored to address the FCT problems efficiently. OLCSO draws inspiration from offline learning, where particles benefit from the experiences of high performers. The algorithm incorporates (i) a ranking-based mechanism where losers learn from peer-to-peer winners based on their ranks, (ii) a two-phase cooperative evolutionary mechanism enhancing searchability and convergence of the algorithm. In the first phase, losers learn from personal best experiences and the shifted center of the population, boosting diversity. In the second phase, losers learn from winners and the center of the population, improving exploitation, (iii) a mutation strategy is embedded to update winner locations in each evolutionary procedure, and (iv) to ensure a feasible solution to FCT problems, the paper also introduces negative and fractional repair mechanisms. OLCSO is applied to solve two sets of FCT problems, linear and non-linear. Experimental results are compared with various heuristic and metaheuristic techniques, commonly used for these problems, using diverse metrics. A comparative analysis of OLCSO’s design elements is also conducted. The results demonstrate OLCSO’s superiority over existing algorithms.

A novel exploration strategy for the YUKI algorithm for topology optimization with metaheuristic structural binary distribution

The YUKI algorithm is an optimization approach based on search space reduction, adjusting its exploration and exploitation strategies based on optimization progress. This article suggests an update to the exploration strategy to enhance its efficacy in engineering design problems and maintain the simplicity of the algorithm. Performance evaluations were conducted on challenging composite functions and engineering design problems. In addition, the metaheuristic structural binary-distribution technique is introduced, integrating the YUKI algorithm with gradient descent for topology optimization. This technique is tested on the problem of maximizing structural stiffness, based on strain energy, across low and high dimensions, and in the problem of heat dissipation. The results suggest a significant improvement in exploration performance. MATLAB and Python source codes for the YUKI algorithm are publicly accessible at https://brahimbenaissa.com/posts/Yuki-Algorithm-02/

Deep learning methodologies based on metaheuristics for predictive engine maintenance

Recently, there has been an increase in concerns about the accessibility, security, and reliability of aviation engines. To prevent engine failures which can be quite serious, it is important to take effective measures. The objective is to create a deep learning simulation that can accurately predict an aircraft engine's viability and remaining usefulness using meta-heuristic techniques to improve its performance. These techniques discover the optimal hyper parameters and architecture for the deep learning model. This will help minimize downtime and maintenance costs for the aircraft fleet by handling complex data such as sensor readings and past maintenance records while also adapting to changing conditions over time. Since training deep learning models can be computationally intensive, meta-heuristic methods increase their robustness. The aim is to enhance performance by increasing the accuracy rate and reducing mean squared losses of multiple deep learning methods used for predicting aircraft engine maintenance by hybridizing them with metaheuristic algorithms.

Predicting daily heating energy consumption in residential buildings through integration of random forest model and meta-heuristic algorithms

This research utilizes a sophisticated hybrid model integrating the Random Forest algorithm with meta-heuristic optimization techniques to estimate heating energy consumption in residential buildings. The study addresses key variables including architectural characteristics, occupancy, and ambient temperature. The primary objective is to enhance the prediction accuracy of heating energy consumption using a novel approach combining Random Forest with various meta-heuristic algorithms. The study employs six combinations of the Random Forest algorithm and meta-heuristic optimizers. To mitigate overfitting, K-Fold cross-validation is implemented during model training. The model's performance is evaluated using five statistical indices: coefficient of determination (R2), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Relative Absolute Error (RAE), and Theil Inequality Coefficient (TIC). Results demonstrate the hybrid model's high predictive accuracy, with the Arithmetic Optimization Algorithm enhancing Random Forest's performance significantly. Notable statistical achievements include R2 = 0.977201, RMSE = 0.1179, MAE = 0.0573, RAE = 0.0930, and TIC = 0.0187. Additionally, the Ant Lion Optimizer shows excellent convergence, achieving a TIC value of 0.014986 after 101 iterations. The proposed hybrid model significantly outperforms traditional methods in predicting residential heating energy consumption. The integration of Random Forest with advanced meta-heuristic algorithms offers a robust framework for enhancing prediction accuracy in energy consumption modeling.

Optimal multivariate mixture: a genetic algorithm approach

AbstractThe Optimal Multivariate Mixture Problem (OMMP) consists of finding an optimal mixture which, starting from a set of elements (items) described by a set of variables (features), is as close as possible to an ideal solution. This problem has numerous applications spanning various fields, including food science, agriculture, chemistry, materials science, medicine, and pharmaceuticals. The OMMP is a class of optimization problems that can be addressed using traditional Operations Research (OR) approaches. However, it can also be effectively tackled using meta-heuristic techniques within Artificial Intelligence (AI). This paper aims to present an Artificial Intelligence perspective. It proposes a Genetic Algorithm (GA) for Optimal Multivariate Mixture (GA-OMM), a novel improved version of a GA whose modified genetic operators prove to improve the exploration efficiency. Here, the algorithm is described in its general framework, and a test case 8-items 5-features is conducted to evaluate efficiency by exploring various combinations of hyperparameters. Test cases are also set up for the previous version, as well as a linear programming (LP) approach. The data experiments indicate that the proposed GA is efficient, converges towards the global optimum, consistently outperforms its predecessor, and delivers highly competitive results. In particular, GA-OMM shows an average fitness of GA-OMMP/LP and standard deviation with an order of magnitude ranging between $$10^{-8}$$ 10 - 8 to $$10^{-4}$$ 10 - 4 . Moreover, it consistently outperforms its predecessor, which exhibits similar values around $$10^{-3}$$ 10 - 3

Meta Heuristic Technique with Reinforcement Learning for Node Deployment in Wireless Sensor Networks

Wireless Sensor Networks (WSNs) are vital in applications like environmental monitoring, smart homes, and battlefield surveillance. Comprising small devices with limited resources, WSNs require efficient node deployment for power optimization and prolonged network lifetime, ensuring sufficient coverage and connectivity. This study introduces an Intelligent Satin Bower Bird Optimizer augmented with reinforcement learning (ISBO-RL), enhancing coverage and connectivity. ISBO-RL focuses on optimal sensor placement for improved coverage and connectivity, using an Optimum Position Finding (OPF) method to identify key sensor node locations. Reinforcement learning is integrated into the ISBO algorithm, allowing nodes to adapt based on performance and changing conditions. Experimental results on diverse platforms highlight ISBO-RL’s efficacy and its superior coverage and connectivity performance as compared to other algorithms. ISBO-RL represents a significant advancement in the field of Wireless Sensor Networks, offering a promising solution to address the challenges of efficient node deployment and network optimization in various critical applications.

Optimal parameters identification for PEMFC using autonomous groups particle swarm optimization algorithm

The precise model for Polymer Electrolyte Membrane Fuel Cells (PEMFCs) is vital for simulation, control, and performance analysis of PEMFCs. It is crucial to accurately estimate the model parameters. Over the past decade, the extraction of unknown parameters of PEMFCs model is formulated as optimization problem and several meta-heuristic techniques have emerged to solve this problem. Despite the development of these techniques to tackle the problem, the slow convergence rate and susceptibility to being trapped in local minima are regarded as weaknesses of these methods. Additionally, because the PEMFC model is a nonlinear and complex model, not all optimization algorithms are suitable for solving it. This article introduces a novel approach that utilizes the Autonomous Groups Particle Swarm Optimization (AGPSO) algorithm for extracting precise values for uncertain parameters inherent in PEMFC model of 250Wstack and BCS-500W stack utilized significantly in the literature. The optimization problem's fitness function is formulated as the total squared errors (TSEs) between the voltage datasets measured and estimated. Three different versions of AGPSO algorithm are presented. Statistical analysis is performed on these three versions to assess their robustness, and the most robust version is identified. Furthermore, the performance of the most robust version is extensively tested and analyzed through a complete comparison with recent optimization algorithms findings from the updated state-of-the-art literature such as BO, QOBO, TGA, HHO and ASO. Further, a statistical analysis was carried out that ensured the reliability and robustness of the introduced AGPSO. The results highlight the efficacy and feasibility of AGPSO-based approach across all compared algorithms, demonstrating an enhancement in the accuracy of the PEMFC model. A two-phase sensitivity analysis, conducted through Monte Carlo Simulation (MCS), was employed to assess how variations in optimized parameters affect the objective function (TSEs). Furthermore, the uncertainty in the maximum power reference current is identified.