An evolutionary Nelder–Mead slime mould algorithm with random learning for efficient design of photovoltaic models

The efficiency of solar cells in converting solar energy into electrical energy can be improved by efficient and accurate solar photovoltaic cell modelling. However, the key to solar photovoltaic cell modelling is the accuracy of the solar cell parameters. Therefore, to obtain the unknown parameters...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xuemeng Weng, Ali Asghar Heidari, Guoxi Liang, Huiling Chen, Xinsheng Ma
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Slime mould algorithm Random learning mechanism Nelder–Mead simplex algorithm Parameter extraction Solar cell Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/2543b7d6bb364b38bfdab155ee231fe3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2543b7d6bb364b38bfdab155ee231fe3
record_format	dspace
spelling	oai:doaj.org-article:2543b7d6bb364b38bfdab155ee231fe32021-11-28T04:34:26ZAn evolutionary Nelder–Mead slime mould algorithm with random learning for efficient design of photovoltaic models2352-484710.1016/j.egyr.2021.11.019https://doaj.org/article/2543b7d6bb364b38bfdab155ee231fe32021-11-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2352484721011653https://doaj.org/toc/2352-4847The efficiency of solar cells in converting solar energy into electrical energy can be improved by efficient and accurate solar photovoltaic cell modelling. However, the key to solar photovoltaic cell modelling is the accuracy of the solar cell parameters. Therefore, to obtain the unknown parameters of the solar cell accurately and efficiently, we proposed an improved slime mould algorithm (ISMA) combining the Nelder–Mead simplex (NMs) mechanism with a random learning mechanism. Specifically, the NMs mechanism ensures that the population is intensive and keeps moving closer to food as the population evolves. At the same time, the random learning mechanism incorporating the monitoring mechanism encourages optimal individuals to continuously learn the results of random communication among different agents and effectively improves the local search capability of the traditional SMA. To validate the performance of the proposed ISMA, it has been utilized to identify the optional parameters of a single diode, double diode, and PV modules. Based on experimental results, it is shown that ISMA outperforms most existing techniques in terms of convergence accuracy, convergence speed, and stability. In addition, ISMA also shows excellent stability in identifying the unknown parameters of three commercial photovoltaic modules under different environmental conditions. In summary, the proposed ISMA can be a promising technology in extracting the parameters of the photovoltaic models.Xuemeng WengAli Asghar HeidariGuoxi LiangHuiling ChenXinsheng MaElsevierarticleSlime mould algorithmRandom learning mechanismNelder–Mead simplex algorithmParameter extractionSolar cellElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENEnergy Reports, Vol 7, Iss , Pp 8784-8804 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Slime mould algorithm Random learning mechanism Nelder–Mead simplex algorithm Parameter extraction Solar cell Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Slime mould algorithm Random learning mechanism Nelder–Mead simplex algorithm Parameter extraction Solar cell Electrical engineering. Electronics. Nuclear engineering TK1-9971 Xuemeng Weng Ali Asghar Heidari Guoxi Liang Huiling Chen Xinsheng Ma An evolutionary Nelder–Mead slime mould algorithm with random learning for efficient design of photovoltaic models
description	The efficiency of solar cells in converting solar energy into electrical energy can be improved by efficient and accurate solar photovoltaic cell modelling. However, the key to solar photovoltaic cell modelling is the accuracy of the solar cell parameters. Therefore, to obtain the unknown parameters of the solar cell accurately and efficiently, we proposed an improved slime mould algorithm (ISMA) combining the Nelder–Mead simplex (NMs) mechanism with a random learning mechanism. Specifically, the NMs mechanism ensures that the population is intensive and keeps moving closer to food as the population evolves. At the same time, the random learning mechanism incorporating the monitoring mechanism encourages optimal individuals to continuously learn the results of random communication among different agents and effectively improves the local search capability of the traditional SMA. To validate the performance of the proposed ISMA, it has been utilized to identify the optional parameters of a single diode, double diode, and PV modules. Based on experimental results, it is shown that ISMA outperforms most existing techniques in terms of convergence accuracy, convergence speed, and stability. In addition, ISMA also shows excellent stability in identifying the unknown parameters of three commercial photovoltaic modules under different environmental conditions. In summary, the proposed ISMA can be a promising technology in extracting the parameters of the photovoltaic models.
format	article
author	Xuemeng Weng Ali Asghar Heidari Guoxi Liang Huiling Chen Xinsheng Ma
author_facet	Xuemeng Weng Ali Asghar Heidari Guoxi Liang Huiling Chen Xinsheng Ma
author_sort	Xuemeng Weng
title	An evolutionary Nelder–Mead slime mould algorithm with random learning for efficient design of photovoltaic models
title_short	An evolutionary Nelder–Mead slime mould algorithm with random learning for efficient design of photovoltaic models
title_full	An evolutionary Nelder–Mead slime mould algorithm with random learning for efficient design of photovoltaic models
title_fullStr	An evolutionary Nelder–Mead slime mould algorithm with random learning for efficient design of photovoltaic models
title_full_unstemmed	An evolutionary Nelder–Mead slime mould algorithm with random learning for efficient design of photovoltaic models
title_sort	evolutionary nelder–mead slime mould algorithm with random learning for efficient design of photovoltaic models
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/2543b7d6bb364b38bfdab155ee231fe3
work_keys_str_mv	AT xuemengweng anevolutionaryneldermeadslimemouldalgorithmwithrandomlearningforefficientdesignofphotovoltaicmodels AT aliasgharheidari anevolutionaryneldermeadslimemouldalgorithmwithrandomlearningforefficientdesignofphotovoltaicmodels AT guoxiliang anevolutionaryneldermeadslimemouldalgorithmwithrandomlearningforefficientdesignofphotovoltaicmodels AT huilingchen anevolutionaryneldermeadslimemouldalgorithmwithrandomlearningforefficientdesignofphotovoltaicmodels AT xinshengma anevolutionaryneldermeadslimemouldalgorithmwithrandomlearningforefficientdesignofphotovoltaicmodels AT xuemengweng evolutionaryneldermeadslimemouldalgorithmwithrandomlearningforefficientdesignofphotovoltaicmodels AT aliasgharheidari evolutionaryneldermeadslimemouldalgorithmwithrandomlearningforefficientdesignofphotovoltaicmodels AT guoxiliang evolutionaryneldermeadslimemouldalgorithmwithrandomlearningforefficientdesignofphotovoltaicmodels AT huilingchen evolutionaryneldermeadslimemouldalgorithmwithrandomlearningforefficientdesignofphotovoltaicmodels AT xinshengma evolutionaryneldermeadslimemouldalgorithmwithrandomlearningforefficientdesignofphotovoltaicmodels
_version_	1718408306313134080

An evolutionary Nelder–Mead slime mould algorithm with random learning for efficient design of photovoltaic models

Ejemplares similares