Improved Grey Wolf Optimization Algorithm Research Articles

An Improved Grey Wolf Optimizer(IGWO) algorithm for optimization of centrifugal pump with guide vane

Abstract To improve the hydraulic performance of a centrifugal pump with guide vane, an improved grey wolf optimizer (IGWO) algorithm is proposed. First, the IGWO algorithm enhances the diversity and global exploration of the initial population with optimal Latin hypercube sampling. Then, the convergence factor is improved by combining the Tanh function to meet the needs of complex non-linear optimization problems. Finally, a search mechanism that enhances population communication is constructed and combined with a mutation-driven search scheme to improve the ability to avoids the local optima traps. The results show that IGWO algorithm has obvious advantages in convergence speed and robustness when dealing with complex non-linear optimization problems. Additionally, satisfactory results are achieved in the application of centrifugal pump optimization. The efficiency of optimized pump reaches 87.8%, which is 1.2% higher than that of the original pump. The anti-cavitation performance of the centrifugal pump is enhanced by improving the distribution of blade inlet attack angles. The vortex area inside the optimized pump impeller is reduced over a large area, and the operating stability of the pump, the matching between the impeller and the guide vane, and the flow characteristics in the guide vane domain are all improved.

Parameter Identification of PMSG-Based Wind Turbine Based on Sensitivity Analysis and Improved Gray Wolf Optimization

With the large-scale integration of wind power, it is essential to establish an electromagnetic transient (EMT) model of a wind turbine system. Focusing on the problem of the difficulty in obtaining the parameters of the direct-driven permanent magnet synchronous generator (PMSG) model, this manuscript proposes a method based on trajectory sensitivity analysis and improved gray wolf optimization (IGWO) for identifying the parameters of the PMSG EMT model. First, a model of a PMSG wind turbine is established on an EMT simulation platform. Then, the key parameters of the model are determined based on the sensitivity analysis. Five control parameters are selected as the key parameters for their higher sensitivity indexes. Finally, the key parameters are accurately identified, using the proposed IGWO algorithm. The final case study demonstrates that the proposed IGWO algorithm has better optimization performance compared with the GWO algorithm and particle swarm optimization (PSO) algorithm. In addition, the simulation waveforms show that the identified parameters are accurate and applicable to other operating conditions.

Runoff prediction based on the IGWOLSTM model: Achieving accurate flood forecasting and emergency management

With the acceleration of global climate change and urbanization, the frequency and impact of flood disasters are increasing year by year, making flood emergency management increasingly crucial for safeguarding people’s lives, property, and societal stability. To enhance the accuracy of river flow prediction, this study employs an Improved Gray Wolf Optimization Algorithm (IGWO) to optimize parameters of the Long Short-Term Memory Network (LSTM) model. Experimental results demonstrate that the proposed algorithm significantly improves the accuracy of river flow prediction, achieving higher precision and better generalization compared to traditional machine learning algorithms. This method provides more reliable data support for flood warning systems, aiding in the accurate prediction of flood occurrence timing and intensity, thereby providing scientific basis for flood prevention and mitigation efforts. Moreover, this approach supports hydro-logical research, enhancing understanding of river water cycle processes and ecosystem changes.

Synthesis of sparse rectangular planar arrays with weight function and improved grey wolf optimization algorithm

AbstractThe present article proposes a novel hybrid approach for addressing the synthesis problem of rectangular planar arrays under multiple constraints, through joint optimization of the weight function and the improved grey wolf optimization (IGWO) algorithm. Firstly, the grey wolf optimization (GWO) algorithm is improved by using tent chaotic mapping, nonlinear convergence factor, dominant wolf dynamic belief strategy, and opposition‐based learning strategy to increase the population diversity and the ability to jump out of the local optimum. Secondly, the array elements are weighted using the weight function to generate the position distribution matrix, which reduces the thinned matrix optimization time and improves the optimization efficiency. Finally, the position distribution matrix is used to generate the thinned array, and the IGWO algorithm is applied to perform the sparse optimization with multiple constraints. The effectiveness of the method is verified through numerical simulation and full‐wave simulation experiments, demonstrating its capability to enhance array antenna performance and reduce peak sidelobe level (PSLL). These experimental results hold significant engineering implications and provide valuable references for addressing the array distribution problem under multiple constraints.

Power efficiency improvement in reactive power dispatch under load uncertainty

Nowadays, there is a significant rise in electricity demand, posing challenges for power grid operators due to inaccurate forecasting, leading to excessive power losses and voltage instability. This paper addresses these issues by focusing on solving optimal reactive power dispatch (ORPD) while considering load demand uncertainty. The main objective of solving ORPD is to reduce power losses by adjusting generator voltage ratings, transformer tap ratio, and shunt capacitors' reactive power. Monte Carlo simulation (MCS) is employed to generate load scenarios using the normal probability density function, while a reduction-based technique is implemented to decrease the number of those scenarios. The improved gray wolf optimization (I-GWO) algorithm is introduced for the first time to address the stochastic ORPD problem. Experimentation is conducted on an IEEE-30 bus system when results are contrasted with conventional gray wolf optimization (GWO) and five other algorithms as stated in the literature. The I-GWO algorithm's performance is assessed with and without considering load demand uncertainty. Through Friedman's statistical tests, a significant decrease of 20.96% in active power losses and 63.06% in the summation of expected power losses is observed. The I-GWO algorithm's results on the ORPD problem demonstrate its effectiveness and robustness.

Grey wolf‐based heuristic methods for accurate parameter extraction to optimize the performance of PV modules

AbstractParameterprediction for PV solar cells plays a crucial role in controlling andoptimizing the performance of PV modules. In this study, the parameter prediction of a four‐diode PV model wascarried out using the Improved Grey Wolf Optimization (IGWO) algorithm, whichbuilds upon the Grey Wolf Optimization (GWO) algorithm. The parameters requiredfor the four‐diode PV model were optimized based on a predefined objectivefunction. Subsequently, the obtained data were compared with the data from RTCFrance Solar Cell to validate the accuracy and reliability of the optimizationresults. The evaluation of the optimization results revealed that the SumSquare Error (SSE) values for PSOGWO, AGWOCS, GWOCS, and GWO were 3.96E‐05, while the MSE value for IGWO was 3.6309E‐05. These findings clearly demonstratethat the proposed IGWO algorithm outperforms the other algorithms used in thestudy, based on the minimized SSE values. This study emphasizes the importanceof parameter prediction in optimizing PV performance, and it contributes to thefield by introducing the novel IGWO algorithm for the four‐diode PV model. Thealgorithm's superior performance, as demonstrated through extensive testing andcomparison with existing algorithms, validates its efficacy in accuratelypredicting the parameters for the PV solar cell model.

Study on PV Power Prediction Based on VMD-IGWO-LSTM

This research proposes a combined approach for predicting photovoltaic power by integrating variational modal decomposition (VMD), an improved gray wolf optimization algorithm (IGWO), and long- and short-term memory neural network (LSTM) techniques. The model takes into account the impact of varying environmental factors on photovoltaic power and aims to enhance prediction accuracy. Firstly, the four environmental factors constraining the PV output power are decomposed into eigenfunctions (IMFs) through variational modal decomposition; then the improved gray wolf optimization algorithm is used to optimize the long and short-term memory neural network; finally, the dimensionality-reduced dataset is inputted into the LSTM neural network, and the dynamic temporal modeling and comparative analysis on the multivariate feature sequences are carried out. The results show that the VMD-LSTM model optimized by the improved Gray Wolf algorithm predicts better than the comparison models LSTM, VMD-LSTM and VMD-GWO-LSTM, and achieves the accurate prediction of time-volt power in the external environmental changes.

Modeling and parameter identification of rate-dependent hysteresis behavior based on modified-generalized Prandtl–Ishlinskii model

The intrinsic characteristic of piezoelectric actuators (PEA), known as hysteresis, has been demonstrated to diminish the capability and stability of the system significantly. This paper proposes a modified-generalized Prandtl–Ishlinskii (MGPI) model to describe the rate-dependent hysteresis in piezoelectric actuators. The developed model incorporates a voltage change rate function to replace the first part of the generalized Prandtl–Ishlinskii (GPI) model. Additionally, the model integrates the cubic polynomial into the envelope function, along with the dynamic thresholds and weights. When describing the hysteresis of the piezoelectric actuator (PEA), the model parameters are identified using the Improved Grey Wolf Optimizer (IGWO) algorithm. To prevent the algorithm from getting trapped in local optima, the cubic chaotic mapping is utilized for population initialization, as well as a nonlinear convergence factor, and the Levy flight strategy factor is introduced to update the Wolf pack’s position. The rate-dependent hysteresis behavior of a PEA under excitation in the 1–200 Hz frequency range was experimentally measured. The measured data were used to demonstrate the validity of the proposed MGPI model. The relative root-mean-square error and the relative maximum error of the MGPI model are 1.41% and 6.00%, respectively, which are lower than those of the GPI model, which are 3.15% and 10.58%. Under the composite frequency driving, the outputs of the GPI model and MGPI model were compared with the measured data of the PEA, the results suggest that the MGPI model and the IGWO algorithm can more accurately describe the rate-dependent hysteresis of the piezoelectric actuators.

Application of optimized Kalman filtering in target tracking based on improved Gray Wolf algorithm

High precision is a very important index in target tracking. In order to improve the prediction accuracy of target tracking, an optimized Kalman filter approach based on improved Gray Wolf algorithm (IGWO-OKF) is proposed in this paper. Since the convergence speed of traditional Gray Wolf algorithm is slow, meanwhile, the number of gray wolves and the choice of the maximum number of iterations has a great influence on the algorithm, a nonlinear control parameter combination adjustment strategy is proposed. An improved Grey Wolf Optimization algorithm (IGWO) is formed by determining the best combination of adjustment parameters through the fastest iteration speed of the algorithm. The improved Grey Wolf Optimization algorithm (IGWO) is formed, and the process noise covariance matrix and observation noise covariance matrix in Kalman filter are optimized by IGWO. The proposed approach is applied into. The experiment results show that the proposed IGWO-OKF approach has low error, high accuracy and good prediction effect.

Research on Dynamic Economic Dispatch Optimization Problem Based on Improved Grey Wolf Algorithm

The dynamic economic dispatch (DED) problem is a typical complex constrained optimization problem with non-smooth, nonlinear, and nonconvex characteristics, especially considering practical situations such as valve point effects and transmission losses, and its objective is to minimize the total fuel costs and total carbon emissions of generating units during the dispatch cycle while satisfying a series of equality and inequality constraints. For the challenging DED problem, a model of a dynamic economic dispatch problem considering fuel costs is first established, and then an improved grey wolf optimization algorithm (IGWO) is proposed, in which the exploitation and exploration capability of the original grey wolf optimization algorithm (GWO) is enhanced by initializing the population with a chaotic algorithm and introducing a nonlinear convergence factor to improve weights. Furthermore, a simple and effective constraint-handling method is proposed for the infeasible solutions. The performance of the IGWO is tested with eight benchmark functions selected and compared with other commonly used algorithms. Finally, the IGWO is utilized for three different scales of DED cases, and compared with existing methods in the literature. The results show that the proposed IGWO has a faster convergence rate and better global optimization capabilities, and effectively reduces the fuel costs of the units, thus proving the effectiveness of IGWO.

Energy-saving optimal scheduling under multi-mode “source-network-load-storage” combined system in metro station based on modified GrayWolf Algorithm

Aiming to address power consumption issues of various equipment in metro stations and the inefficiency of peak shaving and valley filling in the power supply system, this study presents an economic optimization scheduling method for the multi-modal “source-network-load-storage” system in metro stations. The proposed method, called the Improved Gray Wolf Optimization Algorithm (IGWO), utilizes objective evaluation criteria to achieve economic optimization. First, construct a mathematical model of the “sourcenetwork- load-storage” joint system with the metro station at its core. This model should consider the electricity consumption within the station. Secondly, a two-layer optimal scheduling model is established, with the upper model aiming to optimize peak elimination and valley filling, and the lower model aiming to minimize electricity consumption costs within a scheduling cycle. Finally, this paper introduces the IGWO optimization approach, which utilizes meta-models and the Improved Gray Wolf Optimization Algorithm to address the nonlinearity and computational complexity of the two-layer model. The analysis shows that the proposed model and algorithm can improve the solution speed and minimize the cost of electricity used by about 5.5% to 8.7% on the one hand, and on the other hand, it improves the solution accuracy, and at the same time effectively realizes the peak shaving and valley filling, which provides a proof of the effectiveness and feasibility of the new method.

A grey wolf optimization algorithm for solving partial destructive disassembly line balancing problem consider feasibility evaluation and noise pollution

Partial destructive disassembly (PDD) is a crucial tool for enhancing efficiency and reducing disassembly costs when recycling complex end-of-life (EOL) products. Evaluating the feasibility of PDD is crucial for determining its implementation. However, the existing partial destructive disassembly line balancing (PDDLB) problem prioritizes profitability and randomly selects components for destructive, disregarding the feasibility of PDD and the noise pollution resulting from destructive operations. To address this concern, this paper introduces the integration of feasibility evaluation and noise considerations into the PDDLB problem for the first time. Subsequently, a mathematical model is established for the PDDLB problem, aiming to minimize disassembly costs, achieve smoothness balance, minimize the number of stations, and mitigate the adverse effects of noise. Then, an improved grey wolf optimization algorithm (IGWOA) considering feasibility evaluation and noise limitations is developed. It non-linearizes the convergence factor to enhance accuracy in the search for optimality, introduces a Lévy flight operation to further expand the search solution space, and incorporates an interference factor to prevent local optimality. In addition, the superiority of the proposed algorithm in solving different cases is verified by comparing five algorithms for the 25-task example and seven algorithms for the 52-task example in the latest literature. Finally, the proposed method is applied to a real engine case. The obtained results are compared with several classical Swarm Intelligence methods. The comparison results show that IGWOA has advantages due to other group intelligence methods in solving small, medium, and large-scale example. Moreover, the disassembly cost is comparatively low.

OPTIMAL SIZING OF SOLAR-WIND HYBRID MICROGRID USING IMPROVED GREY WOLF OPTIMIZATION ALGORITHM A CASE STUDY OF KADUNA - NIGERIA

This paper presents an improved grey wolf optimization algorithm (IGWOA) for optimal sizing of an isolated photovoltaic (PV), wind turbine (WT), and battery energy storage (BES) hybrid microgrid. To demonstrate the effectiveness of the proposed approach, atmospheric data sets comprising of wind, solar, and temperature of Kaduna International Airport were collected from Nigerian Meteorological Agency while the load demand data was collected from Kaduna International Airport Electricity Distribution Center. The microgrid optimal sizing was formulated as a constrained single objective optimization problem. Constraints including, loss of power supply probability (LPSP), power balance, generation limits and battery state of charge (SOC) were imposed. Three simulation scenarios were considered. Firstly, the target allowable maximum LPSP was fixed at 25% and the algorithm was able to determine the optimal sizing of the hybrid microgrid components and minimize the initial cost from 169,880.00 USD to 112,356.40 USD per annum resulting in 34% savings in cost. Secondly, the effect of the target allowable maximum LPSP variation was investigated, and it was found that the total installed capacity of the system decreases with increase in LPSP thereby decreasing the total cost. Additionally, a novel electricity price index (EPI) was introduced in order to quantify the degree of optimality of the solution. The EPI was found to increase exponentially with increase in LPSP, resulting in an EPI of < 0.05USD/kWh at 20% LPSP. Lastly, to validate the proposed approach, a comparative analysis between the IGWOA and other algorithms was carried out, and the proposed IGWOA proved applicable.

Improving the Control Strategy of the DVR Compensator Based on an Adaptive Notch Filter with an Optimized PD Controller Using the IGWO Algorithm

One of the objectives of electrical distribution networks is to provide customers with access to high‐quality electricity. Because any disruptions in these systems result in voltage disorders, different devices are employed to offset these disruptions on consumers who are more susceptible. One of the most important and contemporary pieces of equipment that is connected in series with the network is dynamic voltage restoration (DVR), which shields delicate loads from network voltage issues by injecting the proper voltage. This article presents a DVR control scheme optimized with improved grey wolf optimization (IGWO) that uses a proportional derivative (PD) controller and adaptive notch filter (ANF). The output LC filter’s resistance has been removed, and the control system has actively engaged in oscillation damping in order to accelerate dynamic responsiveness and lower system losses. The major component of the voltage, which comprises its frequency, amplitude, and phase, is extracted using ANF. The capacitor current of the output filter in this structure is fed back to the control system and from the current mode control in the inner loop to boost stability. Owing to the occasionally complex dynamic behavior in distribution networks, particularly during a fault, the system’s frequency response has been altered and response speed has been accelerated using the PD controller. This kind of controller is distinguished by its accurate functioning in the presence of frequency deviations and its swifter dynamic reaction in the face of voltage swell and sag. In order to improve the THD and voltage sag indicators of the sensitive load, the PD coefficients were adjusted using the IGWO algorithm. As a consequence, the simulation results demonstrated that the suggested controller performed better than traditional controllers.

Improved super-twisting sliding mode control strategy in permanent magnet synchronous motors for hydrogen fuel cell centrifugal compressor

This paper rigorously addresses the intricate control demands of high-speed, high-pressure, wide adjustable speed range, and high energy utilization efficiency required in hydrogen fuel cell centrifugal compressor, with a focus on the speed control of 40,000 RPM permanent magnet synchronous motors (PMSMs). An improved second-order super twisting sliding mode control (STSMC) strategy is proposed to enhance system stability and robustness by integrating the beetle antennae search (BAS) algorithm and grey wolf optimization (GWO) algorithm. The global search capability of BAS is used to improve the local optima issues of GWO, and then the improved GWO algorithm is utilized to address the issues related to parameter selection and convergence speed inherent in the STSMC. Theoretical validity of the proposed strategy is asserted through Quadratic Lyapunov Function, and its practicality is affirmed by thorough simulation. Comparative analyses are conducted with PI controller, traditional Sliding Mode Controller (SMC), and standard Super-Twisting Sliding Mode Controller (ST) under several case studies to show the superiority of the propose STSMC.

Support Vector Regression-Based Operational Effectiveness Evaluation Approach to Reconnaissance Satellite System

As one of the most important part of weapon system of systems (WSoS), quantitative evaluation of reconnaissance satellite system (RSS) is indispensable during its construction and application. Aiming at the problem of nonlinear effectiveness evaluation under small sample conditions, we propose an evaluation method based on support vector regression (SVR) to effectively address the defects of traditional methods. Considering the performance of SVR is influenced by the penalty factor, kernel type, and other parameters deeply, the improved grey wolf optimizer (IGWO) is employed for parameter optimization. In the proposed IGWO algorithm, the opposition-based learning strategy is adopted to increase the probability of avoiding the local optima, the mutation operator is used to escape from premature convergence and differential convergence factors are applied to increase the rate of convergence. Numerical experiments of 14 test functions validate the applicability of IGWO algorithm dealing with global optimization. The index system and evaluation method are constructed based on the characteristics of RSS. To validate the proposed IGWO-SVR evaluation method, eight benchmark data sets and combat simulation are employed to estimate the evaluation accuracy, convergence performance and computational complexity. According to the experimental results, the proposed method outperforms several prediction based evaluation methods, verifies the superiority and effectiveness in RSS operational effectiveness evaluation.

Evaluate asphalt pavement frictional characteristics based on IGWO-NGBoost using 3D macro-texture data

Friction, or skid resistance, is an important feature of road pavements. It is influenced by a combination of factors. Accurately predicting the friction coefficient and thus effectively assessing the skid resistance performance is a complex nonlinear problem. For multi-feature and non-linear data, the accuracy of traditional methods is limited. In addition, the prediction accuracy of some methods depends on the original sample size, so it is difficult to achieve accurate prediction under the condition of small sample size. To solve the above problem, the friction coefficient prediction model based on the improved gray wolf optimization (IGWO) and natural gradient boosting (NGBoost) is proposed. First, to ensure the diversity of samples, asphalt mixture specimens with different gradation types are made. Then, friction and three-dimensional (3D) macro-texture data are collected from the specimen surfaces. Next, twenty-seven 3D macro-texture features are extracted from macro-texture data to describe macro-texture details. A correlation coefficient evaluation method is used to eliminate redundant features, and a feature importance analysis model based on gradient boosting model is constructed to obtain the key factors affecting the skid resistance. Finally, the friction coefficient prediction model based on IGWO-NGBoost is constructed. The IGWO algorithm is used to adjust the hyperparameters of NGBoost to optimize the model structure. The results show that IGWO-NGBoost can effectively fit the friction coefficient with a goodness of fit R2 of 97.31% compared with state-of-the-art methods. The model can effectively analyze the change mechanism of pavement skid resistance under the combined influence of multiple factors.

Maximizing energy storage in Microgrids with an amended multi-verse optimizer

Microgrids have emerged as a possible alternative to overcome the difficulties of the combined cooling, heating, and power (CCHP) system in power networks. Energy storage devices are vital for the stable and effective functioning of Microgrids. In this paper, a new modified metaheuristic technique, called the Amended Multiverse Optimizer algorithm (AMVOA) is used to suggest a new method of Microgrid design with energy storage. The Multiverse theory notion served as the inspiration for the metaheuristic optimization method known as the AMVOA. The suggested strategy takes into account the load demand, energy storage technologies, and architecture of a Microgrid with renewable energy sources. The goal is to keep the Microgrid's overall cost as low as possible while preserving its dependability and sustainability. To validate the efficiency of the proposed method, two HRES scenarios are put out, the first of which relies on PV, wind, diesel, and battery power, and the second of which uses PV, diesel, and battery power. To validate the superiority of the proposed method, the method has been compared with five state-of-the-art algorithms, including the Evolutionary Algorithm (EA), Modified Grasshopper Optimization Algorithm (MGOA), Improved Gray Wolf Optimization Algorithm (IGWOA), Improved Arithmetic Optimization Algorithm (IAOA), and the original MVOA. The study compares two scenarios: one with wind, PV, diesel, and battery power and the other with only PV, diesel, and battery power. In scenario 1 (Wind/PV/DG/BESS), the AMVOA algorithm achieves optimal results, resulting in a Net Present Cost (NPC) of $299,010 and an energy cost of $0.2309 per kilowatt-hour. The proposed technique successfully integrates 84.86 % renewable energy sources while meeting defined limitations. The optimal sizing for scenario 2 (PV/DG/BESS) is $333,800 with an energy cost of $0.3451 per kilowatt-hour. The AMVOA algorithm outperforms other algorithms in convergence and provides efficient power management. However, further analysis and evaluation are necessary to assess the robustness, practicality, and reliability of the proposed Microgrid configurations. The outcomes show how the suggested AMVO-based strategy may be used to create the best Microgrid architecture with energy storage. The recommended method may be applied as a decision-making tool for Microgrid planning and design, especially for the integration of renewable energy.

Quantitative stability analysis of complex nonlinear hydraulic turbine regulation system based on accurate calculation

The current stability studies of the hydraulic turbine regulation system (HTRS) mostly adopt the linear hydro-turbine model ignoring its strong nonlinearity, leading to insufficient disclosure of the true characteristics of the HTRS and also causing great inconvenience to the controller parameter tuning. To address this issue, based on the Hopf bifurcation theory, bisection method, and stability criterion, this paper proposes an algorithm (HBBSC) for determining the controller parameter constraint considering the nonlinearity of the hydro-turbine. Firstly, the nonlinear model of the hydro-turbine is constructed based on the model reconstruction strategy (NNGW) combining the backpropagation neural network (BPNN) with the improved grey wolf optimization algorithm (IGWO) to obtain an accurate nonlinear HTRS numerical simulation platform under the power control mode (PCM) and frequency control mode (FCM). Then, the HBBSC-based quantitative calculation procedure of stability region constraint is introduced in detail. Further, in a case study of stability region calculation of HTRS, the HBBSC is applied to calculate the stability region constraint, and the HBBSC-based stability region is verified through a simulation platform. Finally, the stability region of complex HTRS under all operating conditions is calculated based on HBBSC. The results indicate that the HBBSC can replace the traditional methods for stability region calculation during stability analysis of HTRS, outperforming the latter in accuracy and reliability.

Model optimization of a high-power commercial PEMFC system via an improved grey wolf optimization method

Proton exchange membrane fuel cell (PEMFC) models are conventionally established with a set of parameters identified under steady-state operating conditions. However, such an approach is insufficient to accurately capture the dynamic characteristics of multi-parameter changes in real-world scenarios. This paper develops a semi-empirical model for a 110-kW commercial PEMFC system based on its dynamic operation data to remedy the defects. To improve the fitting accuracy of the semi-empirical PEMFC model, an improved grey wolf optimization (IGWO) algorithm is proposed for model parameter identification. The IGWO algorithm adopts chaotic mapping to optimize the initial population distribution, and a random walk strategy is incorporated to boost the local search ability of the traditional grey wolf optimization (GWO) algorithm. The effectiveness of this IGWO algorithm in optimizing the semi-empirical model is experimentally verified on the 110-kW PEMFC system under highly dynamic operating conditions. Results show that the proposed IGWO algorithm can effectively identify the semi-empirical model’s parameters, establishing a stable and robust model that outperforms those based on traditional metaheuristic algorithms such as GWO, particle swarm optimization, and genetic algorithm. The demonstrated improvement renders it as better suited for optimizing PEMFC semi-empirical models under real-world operating conditions.