Maximum Power Point Tracking Based on Reinforcement Learning Using Evolutionary Optimization Algorithms

In this paper, two universal reinforcement learning methods are considered to solve the problem of maximum power point tracking for photovoltaics. Both methods exhibit fast achievement of the MPP under varying environmental conditions and are applicable in different PV systems. The only required kno...

Full description

Bibliographic Details
Main Authors:	Kostas Bavarinos, Anastasios Dounis, Panagiotis Kofinas
Format:	Article
Language:	English
Published:	MDPI AG 2021-01-01
Series:	Energies
Subjects:	maximum power point tracking reinforcement learning q-learning state–action-reward-state–action evolutionary algorithms optimization
Online Access:	https://www.mdpi.com/1996-1073/14/2/335

id	doaj-5cf5cd5293d84435a9b563c1a09d5daf
record_format	Article
spelling	doaj-5cf5cd5293d84435a9b563c1a09d5daf2021-01-10T00:01:06ZengMDPI AGEnergies1996-10732021-01-011433533510.3390/en14020335Maximum Power Point Tracking Based on Reinforcement Learning Using Evolutionary Optimization AlgorithmsKostas Bavarinos0Anastasios Dounis1Panagiotis Kofinas2Industrial Design and Production Engineering, University of West Attica, 250 Thivon & P. Ralli Str, 12241 Egaleo, GreeceBiomedical Engineering, University of West Attica, Ag. Spyridonos 17, 12243 Egaleo, GreeceIndustrial Design and Production Engineering, University of West Attica, 250 Thivon & P. Ralli Str, 12241 Egaleo, GreeceIn this paper, two universal reinforcement learning methods are considered to solve the problem of maximum power point tracking for photovoltaics. Both methods exhibit fast achievement of the MPP under varying environmental conditions and are applicable in different PV systems. The only required knowledge of the PV system are the open-circuit voltage, the short-circuit current and the maximum power, all under STC, which are always provided by the manufacturer. Both methods are compared to a Fuzzy Logic Controller and the universality of the proposed methods is highlighted. After the implementation and the validation of proper performance of both methods, two evolutionary optimization algorithms (Big Bang—Big Crunch and Genetic Algorithm) are applied. The results demonstrate that both methods achieve higher energy production and in both methods the time for tracking the MPP is reduced, after the application of both evolutionary algorithms.https://www.mdpi.com/1996-1073/14/2/335maximum power point trackingreinforcement learningq-learningstate–action-reward-state–actionevolutionary algorithmsoptimization
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Kostas Bavarinos Anastasios Dounis Panagiotis Kofinas
spellingShingle	Kostas Bavarinos Anastasios Dounis Panagiotis Kofinas Maximum Power Point Tracking Based on Reinforcement Learning Using Evolutionary Optimization Algorithms Energies maximum power point tracking reinforcement learning q-learning state–action-reward-state–action evolutionary algorithms optimization
author_facet	Kostas Bavarinos Anastasios Dounis Panagiotis Kofinas
author_sort	Kostas Bavarinos
title	Maximum Power Point Tracking Based on Reinforcement Learning Using Evolutionary Optimization Algorithms
title_short	Maximum Power Point Tracking Based on Reinforcement Learning Using Evolutionary Optimization Algorithms
title_full	Maximum Power Point Tracking Based on Reinforcement Learning Using Evolutionary Optimization Algorithms
title_fullStr	Maximum Power Point Tracking Based on Reinforcement Learning Using Evolutionary Optimization Algorithms
title_full_unstemmed	Maximum Power Point Tracking Based on Reinforcement Learning Using Evolutionary Optimization Algorithms
title_sort	maximum power point tracking based on reinforcement learning using evolutionary optimization algorithms
publisher	MDPI AG
series	Energies
issn	1996-1073
publishDate	2021-01-01
description	In this paper, two universal reinforcement learning methods are considered to solve the problem of maximum power point tracking for photovoltaics. Both methods exhibit fast achievement of the MPP under varying environmental conditions and are applicable in different PV systems. The only required knowledge of the PV system are the open-circuit voltage, the short-circuit current and the maximum power, all under STC, which are always provided by the manufacturer. Both methods are compared to a Fuzzy Logic Controller and the universality of the proposed methods is highlighted. After the implementation and the validation of proper performance of both methods, two evolutionary optimization algorithms (Big Bang—Big Crunch and Genetic Algorithm) are applied. The results demonstrate that both methods achieve higher energy production and in both methods the time for tracking the MPP is reduced, after the application of both evolutionary algorithms.
topic	maximum power point tracking reinforcement learning q-learning state–action-reward-state–action evolutionary algorithms optimization
url	https://www.mdpi.com/1996-1073/14/2/335
work_keys_str_mv	AT kostasbavarinos maximumpowerpointtrackingbasedonreinforcementlearningusingevolutionaryoptimizationalgorithms AT anastasiosdounis maximumpowerpointtrackingbasedonreinforcementlearningusingevolutionaryoptimizationalgorithms AT panagiotiskofinas maximumpowerpointtrackingbasedonreinforcementlearningusingevolutionaryoptimizationalgorithms
_version_	1724343834440105984

Maximum Power Point Tracking Based on Reinforcement Learning Using Evolutionary Optimization Algorithms

Similar Items