干旱区生态环境知识资源中心(Arid): Ultra-short-term exogenous forecasting of photovoltaic power production using genetically optimized non-linear auto-regressive recurrent neural networks

Arid

DOI	10.1016/j.renene.2021.02.103
	Ultra-short-term exogenous forecasting of photovoltaic power production using genetically optimized non-linear auto-regressive recurrent neural networks
	Hassan, Muhammed A.; Bailek, Nadjem; Bouchouicha, Kada; Nwokolo, Samuel Chukwujindu
通讯作者	Hassan, MA (corresponding author), Cairo Univ, Fac Engn, Dept Power Mech Engn, Giza 12613, Egypt. ; Bailek, N (corresponding author), Univ Tamanghasset, Fac Sci & Technol, Dept Matter Sci, Energies & Mat Res Lab, Tamanrasset 10034, Algeria.
来源期刊	RENEWABLE ENERGY
ISSN	0960-1481
EISSN	1879-0682
出版年	2021
卷号	171 页码:191-209
英文摘要	Accurate and credible ultra-short-term photovoltaic (PV) power production prediction is very important in short-term resource planning, electric power dispatching, and operational security for the solar power system. This study proposes a novel approach of using genetically optimized non-linear auto-regressive recurrent neural networks (NARX) for ultra-short-term forecasting of PV power output. Hence, the high prediction accuracy of static multi-layered perceptron neural networks can be extended to dynamic (time-series) models with a more stable learning process. Exogenous models with different commonly available meteorological input parameters are developed and tested at five different locations in Algeria and Australia, as case studies of the arid desert climate. The prediction capabilities of the models are quantified as functions of the forecasting horizon (5, 15, 30, and 60 min) and the number of meteorological inputs using various statistical measures. It was found that the proposed models offer very good estimates of output power, with relative root mean square errors ranging between-10 and-20% and coefficients of determination higher than 91%, while improving the accuracy of corresponding endogenous models by up to 22.3% by only considering the day number and local time as external variables. Unlike the persistent model, the proposed NARX-GA models perform better as the forecasting horizon narrows down, with improvements of up to 58.4%. (c) 2021 Elsevier Ltd. All rights reserved.
英文关键词	Photovoltaic power Resource planning Short-term forecasting NARX Neural network Genetic optimization
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000637514700002
WOS类目	Green & Sustainable Science & Technology ; Energy & Fuels
WOS研究方向	Science & Technology - Other Topics ; Energy & Fuels
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/351561
作者单位	[Hassan, Muhammed A.] Cairo Univ, Fac Engn, Dept Power Mech Engn, Giza 12613, Egypt; [Bailek, Nadjem] Univ Tamanghasset, Fac Sci & Technol, Dept Matter Sci, Energies & Mat Res Lab, Tamanrasset 10034, Algeria; [Bouchouicha, Kada] Ctr Dev Energies Renouvelables CDER, Unite Rech Energies Renouvelables Milieu Saharien, Adrar 01000, Algeria; [Nwokolo, Samuel Chukwujindu] Univ Calabar, Fac Phys Sci, Dept Phys, Calabar, Nigeria
推荐引用方式 GB/T 7714	Hassan, Muhammed A.,Bailek, Nadjem,Bouchouicha, Kada,et al. Ultra-short-term exogenous forecasting of photovoltaic power production using genetically optimized non-linear auto-regressive recurrent neural networks[J],2021,171:191-209.
APA	Hassan, Muhammed A.,Bailek, Nadjem,Bouchouicha, Kada,&Nwokolo, Samuel Chukwujindu.(2021).Ultra-short-term exogenous forecasting of photovoltaic power production using genetically optimized non-linear auto-regressive recurrent neural networks.RENEWABLE ENERGY,171,191-209.
MLA	Hassan, Muhammed A.,et al."Ultra-short-term exogenous forecasting of photovoltaic power production using genetically optimized non-linear auto-regressive recurrent neural networks".RENEWABLE ENERGY 171(2021):191-209.