An intelligent algorithm based on reinforcement learning to identify the parameters of solar systems

Xuming Wang; Wen Zhang; Xiaobing Yu; Xuming Wang; Wen Zhang; Xiaobing Yu

doi:10.3934/jimo.2026174

Journal of Industrial and Management Optimization

2026, Volume 22, Issue 10: 5039-5073. doi: 10.3934/jimo.2026174

Previous Article Next Article

Research article

An intelligent algorithm based on reinforcement learning to identify the parameters of solar systems

1.
Engineering Training Center, Nanjing University of Information Science & Technology, Nanjing 210044, China
2.
School of Management Science and Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, China

Received: 15 July 2026 Revised: 27 August 2026 Accepted: 08 September 2026 Published: 15 September 2026
90C29

Accurately identifying the parameters of solar systems is an essential measure to improve the efficiency of turning solar energy into electrical energy. An intelligent algorithm based on reinforcement learning was developed to identify photovoltaic parameters. The proposed algorithm includes three novelties: i) two new search methods are proposed, namely local search and global search, in which exploitation and exploration of the algorithm are balanced; ii) the ranking strategy is used to determine appropriate search methods for each individual; and iii) the main parameters of two search methods are adjusted by the reinforcement learning technique. To verify the effectiveness of the proposed algorithm in identifying parameters from solar systems, the proposed algorithm was utilized on five photovoltaic models and compared the outcomes with those obtained by other algorithms. The test cases include the single-diode and double-diode models and three photovoltaic panel module models. Performance was assessed using the root mean square error between measured and estimated current values. Ablation experiments examined the contributions of the search strategies, ranking mechanism, and reinforcement learning–based parameter adjustment, while additional comparisons evaluated convergence, stability, and computational time. The final experimental results verified the excellent performance of the proposed algorithm in identifying parameters from solar systems, proving its usefulness in the field of artificial intelligence.
- solar systems,
- parameter identification,
- reinforcement learning,
- optimization algorithm,
- photovoltaic models,
- hybrid heuristic algorithm
Citation: Xuming Wang, Wen Zhang, Xiaobing Yu. An intelligent algorithm based on reinforcement learning to identify the parameters of solar systems[J]. Journal of Industrial and Management Optimization, 2026, 22(10): 5039-5073. doi: 10.3934/jimo.2026174

Related Papers:

Abstract

Accurately identifying the parameters of solar systems is an essential measure to improve the efficiency of turning solar energy into electrical energy. An intelligent algorithm based on reinforcement learning was developed to identify photovoltaic parameters. The proposed algorithm includes three novelties: i) two new search methods are proposed, namely local search and global search, in which exploitation and exploration of the algorithm are balanced; ii) the ranking strategy is used to determine appropriate search methods for each individual; and iii) the main parameters of two search methods are adjusted by the reinforcement learning technique. To verify the effectiveness of the proposed algorithm in identifying parameters from solar systems, the proposed algorithm was utilized on five photovoltaic models and compared the outcomes with those obtained by other algorithms. The test cases include the single-diode and double-diode models and three photovoltaic panel module models. Performance was assessed using the root mean square error between measured and estimated current values. Ablation experiments examined the contributions of the search strategies, ranking mechanism, and reinforcement learning–based parameter adjustment, while additional comparisons evaluated convergence, stability, and computational time. The final experimental results verified the excellent performance of the proposed algorithm in identifying parameters from solar systems, proving its usefulness in the field of artificial intelligence.

References

[1]	Y. B. Assoa, D. Valencia-Caballero, E. Rico, T. D. Caño, J. V. Furtado, Performance of a large size photovoltaic module for façade integration, Renew. Energy, 211 (2023), 903–917. https://doi.org/10.1016/j.renene.2023.04.087 doi: 10.1016/j.renene.2023.04.087
[2]	F. Nicoletti, M. A. Cucumo, N. Arcuri, Building-integrated photovoltaics (BIPV): A mathematical approach to evaluate the electrical production of solar PV blinds, Energy, 263 (2023), 126030. https://doi.org/10.1016/j.energy.2022.126030 doi: 10.1016/j.energy.2022.126030
[3]	S. Li, W. Gong, L. Wang, X. Yan, C. Hu, A hybrid adaptive teaching–learning-based optimization and differential evolution for parameter identification of photovoltaic models, Energ Convers Manage, 225 (2020), 113474. https://doi.org/10.1016/j.enconman.2020.113474 doi: 10.1016/j.enconman.2020.113474
[4]	H. Bakır, Elevating PV model performance: Accurate and reliable parameter extraction of solar cell models with state-of-art metaheuristic algorithms, Next Energy, 11 (2026), 100513. https://doi.org/10.1016/j.nxener.2026.100513 doi: 10.1016/j.nxener.2026.100513
[5]	X. Mi, Z. Liao, S. Li, Q. Gu, Adaptive teaching–learning-based optimization with experience learning to identify photovoltaic cell parameters, Energy Rep, 7 (2021), 4114–4125. https://doi.org/10.1016/j.egyr.2021.06.097 doi: 10.1016/j.egyr.2021.06.097
[6]	Z. Liao, Z. Chen, S. Li, Parameters extraction of photovoltaic models using triple-phase teaching-learning-based optimization, IEEE Access, 8 (2020), 69937–69952. https://doi.org/10.1109/access.2020.2984728 doi: 10.1109/access.2020.2984728
[7]	R. Storn, K. Price, Differential evolution – A simple and efficient heuristic for global optimization over continuous spaces, J. Glob. Optim., 11 (1997), 341–359. https://doi.org/10.1023/A:1008202821328 doi: 10.1023/A:1008202821328
[8]	K. Yu, J. J. Liang, B. Y. Qu, X. Chen, H. Wang, Parameters identification of photovoltaic models using an improved JAYA optimization algorithm, Energy Convers. Manage., 150 (2017), 742–753. https://doi.org/10.1016/j.enconman.2017.08.063 doi: 10.1016/j.enconman.2017.08.063
[9]	F. Hui, S. Li, K. Peng, S. Jing, M. Liu, UMRL: A unified multi-modal reinforcement learning for autonomous driving decision-making at unsignalized intersections, Inf. Fusion, (2026), 104721. https://doi.org/10.1016/j.inffus.2026.104721 doi: 10.1016/j.inffus.2026.104721
[10]	Z. Hu, W. Gong, S. Li, Reinforcement learning-based differential evolution for parameters extraction of photovoltaic models, Energy Rep., 7 (2021), 916–928. https://doi.org/10.1016/j.egyr.2021.01.096 doi: 10.1016/j.egyr.2021.01.096
[11]	A. M. Humada, M. Hojabri, S. Mekhilef, H. M. Hamada, Solar cell parameters extraction based on single and double-diode models: A review, Renew. Sustain. Energy Rev., 56 (2016), 494–509. https://doi.org/10.1016/j.rser.2015.11.051 doi: 10.1016/j.rser.2015.11.051
[12]	F. J. Toledo, V. Galiano, J. M. Blanes, V. Herranz, E. Batzelis, Photovoltaic single-diode model parametrization. An application to the calculus of the Euclidean distance to an I–V curve, Math. Comput. Simul., 225 (2024), 794–819. https://doi.org/10.1016/j.matcom.2023.01.005 doi: 10.1016/j.matcom.2023.01.005
[13]	J. Dang, G. Wang, C. Xia, R. Jia, P. Li, Research on the parameter identification of PV module based on fuzzy adaptive differential evolution algorithm, Energy Rep., 8 (2022), 12081–12091. https://doi.org/10.1016/j.egyr.2022.09.057 doi: 10.1016/j.egyr.2022.09.057
[14]	S. Mirjalili, S. M. Mirjalili, A. Lewis, Grey wolf optimizer, Adv. Eng. Softw., 69 (2014), 46–61. https://doi.org/10.1016/j.advengsoft.2013.12.007 doi: 10.1016/j.advengsoft.2013.12.007
[15]	J. Kennedy, R. Eberhart, Particle swarm optimization, Proc. ICNN'95, 4 (1995), 1942–1948. https://doi.org/10.1109/ICNN.1995.488968 doi: 10.1109/ICNN.1995.488968
[16]	A. Taheri, K. RahimiZadeh, R. V. Rao, An efficient Balanced Teaching-Learning-Based optimization algorithm with Individual restarting strategy for solving global optimization problems, Inf. Sci., 576 (2021), 68–104. https://doi.org/10.1016/j.ins.2021.06.064 doi: 10.1016/j.ins.2021.06.064
[17]	T. Easwarakhanthan, J. Bottin, I. Bouhouch, C. Boutrit, Nonlinear minimization algorithm for determining the solar cell parameters with microcomputers, Int. J. Sol. Energy, 4 (1986), 1–12. https://doi.org/10.1080/01425918608909835 doi: 10.1080/01425918608909835
[18]	K. Yu, B. Qu, C. Yue, S. Ge, X. Chen, J. Liang, A performance-guided JAYA algorithm for parameters identification of photovoltaic cell and module, Appl. Energy, 237 (2019), 241–257. https://doi.org/10.1016/j.apenergy.2019.01.008 doi: 10.1016/j.apenergy.2019.01.008
[19]	J. Zhou, Y. Zhang, Y. Zhang, W. L. Shang, Z. Yang, W. Feng, Parameters identification of photovoltaic models using a differential evolution algorithm based on elite and obsolete dynamic learning, Appl. Energy, 314 (2022), 118877. https://doi.org/10.1016/j.apenergy.2022.118877 doi: 10.1016/j.apenergy.2022.118877
[20]	S. Li, W. Gong, X. Yan, C. Hu, D. Bai, L. Wang, L. Gao, Parameter extraction of photovoltaic models using an improved teaching-learning-based optimization, Energy Convers. Manage., 186 (2019), 293–305. https://doi.org/10.1016/j.enconman.2019.02.048 doi: 10.1016/j.enconman.2019.02.048
[21]	R. V. Rao, V. J. Savsani, D. P. Vakharia, Teaching–learning-based optimization: A novel method for constrained mechanical design optimization problems, Comput. Aided Des., 43 (2011), 303–315. https://doi.org/10.1016/j.cad.2010.12.015 doi: 10.1016/j.cad.2010.12.015
[22]	D. Wu, S. Wang, Q. Liu, L. Abualigah, H. Jia, N. Razmjooy, An improved teaching-learning-based optimization algorithm with reinforcement learning strategy for solving optimization problems, Comput. Intell. Neurosci., 2022 (2022), 1–24. https://doi.org/10.1155/2022/1535957 doi: 10.1155/2022/1535957
[23]	E. Rashedi, H. Nezamabadi-pour, S. Saryazdi, GSA: A gravitational search algorithm, Inf. Sci., 179 (2009), 2232–2248. https://doi.org/10.1016/j.ins.2009.03.004 doi: 10.1016/j.ins.2009.03.004
[24]	D. Karaboga, B. Basturk, A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm, J. Glob. Optim., 39 (2007), 459–471. https://doi.org/10.1007/s10898-007-9149-x doi: 10.1007/s10898-007-9149-x
[25]	K. Yu, X. Chen, X. Wang, Z. Wang, Parameters identification of photovoltaic models using self-adaptive teaching-learning-based optimization, Energy Convers. Manage., 145 (2017), 233–246. https://doi.org/10.1016/j.enconman.2017.04.054 doi: 10.1016/j.enconman.2017.04.054
[26]	G. Xiong, J. Zhang, X. Yuan, D. Shi, Y. He, G. Yao, Parameter extraction of solar photovoltaic models by means of a hybrid differential evolution with whale optimization algorithm, Sol. Energy, 176 (2018), 742–761. https://doi.org/10.1016/j.solener.2018.10.050 doi: 10.1016/j.solener.2018.10.050
[27]	M. A. Elaziz, D. Oliva, Parameter estimation of solar cells diode models by an improved opposition-based whale optimization algorithm, Energy Convers. Manage., 171 (2018), 1843–1859. https://doi.org/10.1016/j.enconman.2018.05.062 doi: 10.1016/j.enconman.2018.05.062
[28]	X. Chen, B. Xu, C. Mei, Y. Ding, K. Li, Teaching–learning–based artificial bee colony for solar photovoltaic parameter estimation, Appl. Energy, 212 (2018), 1578–1588. https://doi.org/10.1016/j.apenergy.2017.12.115 doi: 10.1016/j.apenergy.2017.12.115
[29]	I. Ahmadianfar, W. Gong, A. A. Heidari, N. A. Golilarz, A. Samadi-Koucheksaraee, H. Chen, Gradient-based optimization with ranking mechanisms for parameter identification of photovoltaic systems, Energy Rep., 7 (2021), 3979–3997. https://doi.org/10.1016/j.egyr.2021.06.064 doi: 10.1016/j.egyr.2021.06.064
[30]	W. Long, T. Wu, M. Xu, M. Tang, S. Cai, Parameters identification of photovoltaic models by using an enhanced adaptive butterfly optimization algorithm, Energy, 229 (2021), 120750. https://doi.org/10.1016/j.energy.2021.120750 doi: 10.1016/j.energy.2021.120750
[31]	F. J. Xavier, A. Pradeep, M. Premkumar, C. Kumar, Orthogonal learning-based Gray Wolf Optimizer for identifying the uncertain parameters of various photovoltaic models, Optik, 247 (2021), 167973. https://doi.org/10.1016/j.ijleo.2021.167973 doi: 10.1016/j.ijleo.2021.167973
[32]	Y. Xiong, Y. Luo, J. Peng, Q. Zhang, S. Huang, An improved population segmentation-based multi-mutation differential evolution algorithm for parameter extraction of photovoltaic models, Energy Convers. Manage., 327 (2025), 119553. https://doi.org/10.1016/j.enconman.2025.119553 doi: 10.1016/j.enconman.2025.119553
[33]	X. Jian, Z. Weng, A logistic chaotic JAYA algorithm for parameters identification of photovoltaic cell and module models, Optik, 203 (2020), 164041. https://doi.org/10.1016/j.ijleo.2019.164041 doi: 10.1016/j.ijleo.2019.164041
[34]	J. Liang, K. Qiao, M. Yuan, K. Yu, B. Qu, S. Ge, et al., Evolutionary multi-task optimization for parameters extraction of photovoltaic models, Energy Convers. Manage., 207 (2020), 112509. https://doi.org/10.1016/j.enconman.2020.112509 doi: 10.1016/j.enconman.2020.112509
[35]	D. Oliva, M. A. E. Aziz, A. E. Hassanien, Parameter estimation of photovoltaic cells using an improved chaotic whale optimization algorithm, Appl. Energy, 200 (2017), 141–154. https://doi.org/10.1016/j.apenergy.2017.05.029 doi: 10.1016/j.apenergy.2017.05.029
[36]	X. Chen, K. Yu, Hybridizing cuckoo search algorithm with biogeography-based optimization for estimating photovoltaic model parameters, Sol. Energy, 180 (2019), 192–206. https://doi.org/10.1016/j.solener.2019.01.025 doi: 10.1016/j.solener.2019.01.025
[37]	W. Long, S. Cai, J. Jiao, M. Xu, T. Wu, A new hybrid algorithm based on grey wolf optimizer and cuckoo search for parameter extraction of solar photovoltaic models, Energy Convers. Manage., 203 (2020), 112243. https://doi.org/10.1016/j.enconman.2019.112243 doi: 10.1016/j.enconman.2019.112243
[38]	J. Liang, S. Ge, B. Qu, K. Yu, F. Liu, H. Yang, et al., Classified perturbation mutation based particle swarm optimization algorithm for parameters extraction of photovoltaic models, Energy Convers. Manage., 203 (2020), 112138. https://doi.org/10.1016/j.enconman.2019.112138 doi: 10.1016/j.enconman.2019.112138

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)