Modeling of Photovoltaic Array Based on Multi-Agent Deep Reinforcement Learning Using Residuals of I–V Characteristics

Jingwei Zhang, Zenan Yang, Kun Ding (), Li Feng, Frank Hamelmann, Xihui Chen, Yongjie Liu and Ling Chen
Additional contact information
Jingwei Zhang: College of Mechanical and Electrical Engineering, Hohai University, Changzhou 213022, China
Zenan Yang: College of Mechanical and Electrical Engineering, Hohai University, Changzhou 213022, China
Kun Ding: College of Mechanical and Electrical Engineering, Hohai University, Changzhou 213022, China
Li Feng: Solar Computing Laboratory, University of Applied Sciences Bielefeld, Artilleriestraße 9, 32427 Minden, Germany
Frank Hamelmann: Solar Computing Laboratory, University of Applied Sciences Bielefeld, Artilleriestraße 9, 32427 Minden, Germany
Xihui Chen: College of Mechanical and Electrical Engineering, Hohai University, Changzhou 213022, China
Yongjie Liu: Engineering Research Center of Dredging Technology of Ministry of Education, Changzhou 213022, China
Ling Chen: School of Physics and Electronic Electrical Engineering, Huaiyin Normal University, Huai’an 223300, China

Energies, 2022, vol. 15, issue 18, 1-17

Abstract: Currently, the accuracy of modeling a photovoltaic (PV) array for fault diagnosis is still unsatisfactory due to the fact that the modeling accuracy is limited by the accuracy of extracted model parameters. In this paper, the modeling of a PV array based on multi-agent deep reinforcement learning (RL) using the residuals of I–V characteristics is proposed. The environment state based on the high dimensional residuals of I–V characteristics and the corresponding cooperative reward is presented for the RL agents. The actions of each agent considering the damping amplitude are designed. Then, the entire framework of modeling a PV array based on multi-agent deep RL is presented. The feasibility and accuracy of the proposed method are verified by the one-year measured data of a PV array. The experimental results show that the higher modeling accuracy of the next time step is obtained by the extracted model parameters using the proposed method, compared with that using the conventional meta-heuristic algorithms and the analytical method. The daily root mean square error (RMSE) is approximately 0.5015 A on the first day, and converges to 0.1448 A on the last day of training. The proposed multi-agent deep RL framework simplifies the design of states and rewards for extracting model parameters.

Keywords: deep reinforcement learning; double deep Q network; parameter estimation; photovoltaic mathematical model (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.mdpi.com/1996-1073/15/18/6567/pdf (application/pdf)
https://www.mdpi.com/1996-1073/15/18/6567/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:15:y:2022:i:18:p:6567-:d:909830

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().