Maximum Power Point Tracking of Photovoltaic System Based on Reinforcement Learning
The maximum power point tracking (MPPT) technique is often used in photovoltaic (PV) systems to extract the maximum power in various environmental conditions. The perturbation and observation (P&O) method is one of the most well-known MPPT methods; however, it may face problems of large osci...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/19/22/5054 |
id |
doaj-e34c39d6a2eb413090376443bd17393f |
---|---|
record_format |
Article |
spelling |
doaj-e34c39d6a2eb413090376443bd17393f2020-11-25T02:35:02ZengMDPI AGSensors1424-82202019-11-011922505410.3390/s19225054s19225054Maximum Power Point Tracking of Photovoltaic System Based on Reinforcement LearningKuan-Yu Chou0Shu-Ting Yang1Yon-Ping Chen2Institute of Electrical and Control Engineering, National Chiao Tung University, Hsinchu 30010, TaiwanInstitute of Electrical and Control Engineering, National Chiao Tung University, Hsinchu 30010, TaiwanInstitute of Electrical and Control Engineering, National Chiao Tung University, Hsinchu 30010, TaiwanThe maximum power point tracking (MPPT) technique is often used in photovoltaic (PV) systems to extract the maximum power in various environmental conditions. The perturbation and observation (P&O) method is one of the most well-known MPPT methods; however, it may face problems of large oscillations around maximum power point (MPP) or low-tracking efficiency. In this paper, two reinforcement learning-based maximum power point tracking (RL MPPT) methods are proposed by the use of the Q-learning algorithm. One constructs the Q-table and the other adopts the Q-network. These two proposed methods do not require the information of an actual PV module in advance and can track the MPP through offline training in two phases, the learning phase and the tracking phase. From the experimental results, both the reinforcement learning-based Q-table maximum power point tracking (RL-QT MPPT) and the reinforcement learning-based Q-network maximum power point tracking (RL-QN MPPT) methods have smaller ripples and faster tracking speeds when compared with the P&O method. In addition, for these two proposed methods, the RL-QT MPPT method performs with smaller oscillation and the RL-QN MPPT method achieves higher average power.https://www.mdpi.com/1424-8220/19/22/5054maximum power point tracking (mppt)photovoltaic (pv) systemreinforcement learningq-learningq-network |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Kuan-Yu Chou Shu-Ting Yang Yon-Ping Chen |
spellingShingle |
Kuan-Yu Chou Shu-Ting Yang Yon-Ping Chen Maximum Power Point Tracking of Photovoltaic System Based on Reinforcement Learning Sensors maximum power point tracking (mppt) photovoltaic (pv) system reinforcement learning q-learning q-network |
author_facet |
Kuan-Yu Chou Shu-Ting Yang Yon-Ping Chen |
author_sort |
Kuan-Yu Chou |
title |
Maximum Power Point Tracking of Photovoltaic System Based on Reinforcement Learning |
title_short |
Maximum Power Point Tracking of Photovoltaic System Based on Reinforcement Learning |
title_full |
Maximum Power Point Tracking of Photovoltaic System Based on Reinforcement Learning |
title_fullStr |
Maximum Power Point Tracking of Photovoltaic System Based on Reinforcement Learning |
title_full_unstemmed |
Maximum Power Point Tracking of Photovoltaic System Based on Reinforcement Learning |
title_sort |
maximum power point tracking of photovoltaic system based on reinforcement learning |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2019-11-01 |
description |
The maximum power point tracking (MPPT) technique is often used in photovoltaic (PV) systems to extract the maximum power in various environmental conditions. The perturbation and observation (P&O) method is one of the most well-known MPPT methods; however, it may face problems of large oscillations around maximum power point (MPP) or low-tracking efficiency. In this paper, two reinforcement learning-based maximum power point tracking (RL MPPT) methods are proposed by the use of the Q-learning algorithm. One constructs the Q-table and the other adopts the Q-network. These two proposed methods do not require the information of an actual PV module in advance and can track the MPP through offline training in two phases, the learning phase and the tracking phase. From the experimental results, both the reinforcement learning-based Q-table maximum power point tracking (RL-QT MPPT) and the reinforcement learning-based Q-network maximum power point tracking (RL-QN MPPT) methods have smaller ripples and faster tracking speeds when compared with the P&O method. In addition, for these two proposed methods, the RL-QT MPPT method performs with smaller oscillation and the RL-QN MPPT method achieves higher average power. |
topic |
maximum power point tracking (mppt) photovoltaic (pv) system reinforcement learning q-learning q-network |
url |
https://www.mdpi.com/1424-8220/19/22/5054 |
work_keys_str_mv |
AT kuanyuchou maximumpowerpointtrackingofphotovoltaicsystembasedonreinforcementlearning AT shutingyang maximumpowerpointtrackingofphotovoltaicsystembasedonreinforcementlearning AT yonpingchen maximumpowerpointtrackingofphotovoltaicsystembasedonreinforcementlearning |
_version_ |
1724805780964638720 |