@article{4fca284888e34179acf3623c95d6f98e,
title = "Self-Tuning MPPT Scheme Based on Reinforcement Learning and Beta Parameter in Photovoltaic Power Systems",
abstract = "Maximum power point tracking (MPPT) is required in PV power systems for the highest solar energy harvest. This article proposes a self-tuning scheme to improve the MPPT performance in terms of high accuracy and speed. The scheme adopts the reinforcement learning (RL) and Beta parameter for the highest MPPT performance. The tracking speed and accuracy are significantly improved since the RL algorithm is enhanced for high convergence speed, meanwhile, the guiding variable β is introduced to constrain the exploration space. Simulation and experimental test are applied to validate the superior performance of the proposed solution following the EN50530 dynamic test procedure.",
keywords = "Control engineering, maximum power point tracking (MPPT), optimization, photovoltaic power system, reinforcement learning (RL), self-tuning",
author = "Dingyi Lin and Xingshuo Li and Shuye Ding and Huiqing Wen and Yang Du and Weidong Xiao",
note = "Funding Information: This work was supported in part by the National Natural Science Foundation of China under Grant 51977112 and in part by the Natural Science Research Project of Jiangsu Higher Education Institutions under Grant 20KJB470020. Funding Information: Manuscript received January 26, 2021; revised April 15, 2021; accepted June 12, 2021. Date of publication June 16, 2021; date of current version August 16, 2021. This work was supported in part by the National Natural Science Foundation of China under Grant 51977112 and in part by the Natural 20KJB470020.RecommendedforpublicationbyAssociateEditorC.T.Rim.ScienceResearchProjectofJiangsuHigherEducationInstitutionsunderGrant P HOTOVOLTAIC (PV) power systems grow fast globally (Corresponding author: Xingshuo Li.) as the major sustainable energy source. Maximum power DingyiLin,XingshuoLi,andShuyeDingarewiththeSchoolofElectricaland point tracking (MPPT) is essential to extract maximum power (e-mail:lindingyi@126.com;xingshuo.li@njnu.edu.cn;dingshuye@163.com).AutomationEngineering,NanjingNormalUniversity,Nanjing210023,China from the solar resources in real time regardless of changing Huiqing Wen is with the Xi{\textquoteright}an Jiaotong–Liverpool University, Suzhou weather conditions. Many algorithms for MPPT have been 215123,China(e-mail:Huiqing.Wen@xjtlu.edu.cn). developed to pursue the goal of high accuracy and speed. University,Cairns,QLD4870,Australia(e-mail:yang.du@jcu.edu.au).YangDuiswiththeCollegeof ScienceandEngineering, James Different algorithms for MPPT have been reviewed and com- Weidong Xiao is with the University of Sydney, Sydney, NSW 2006, Australia pared in the past to reveal the pros and cons [1]. The conventional (e-mail:weidong.xiao@sydney.edu.au). MPPT methods include the incremental conductance (INC), hill //doi.org/10.1109/TPEL.2021.3089707.Colorversionsofoneormorefiguresinthisarticleareavailableathttps: climbing (HC), and perturbation and observation (P&O). Such Digital Object Identifier 10.1109/TPEL.2021.3089707 algorithms are based on the fixed step size (FSS), which show 0885-8993 {\textcopyright} 2021 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information. Publisher Copyright: {\textcopyright} 1986-2012 IEEE.",
year = "2021",
month = dec,
doi = "10.1109/TPEL.2021.3089707",
language = "English",
volume = "36",
pages = "13826--13838",
journal = "IEEE Transactions on Power Electronics",
issn = "0885-8993",
number = "12",
}