干旱区生态环境知识资源中心(Arid): Very-Short-Term Power Prediction for PV Power Plants Using a Simple and Effective RCC-LSTM Model Based on Short Term Multivariate Historical Datasets

Arid

DOI	10.3390/electronics9020289
	Very-Short-Term Power Prediction for PV Power Plants Using a Simple and Effective RCC-LSTM Model Based on Short Term Multivariate Historical Datasets
	Chen, Biaowei 1,2,3; Lin, Peijie 1,2,3; Lai, Yunfeng 1,2,3; Cheng, Shuying 1,2,3; Chen, Zhicong 1,2,3; Wu, Lijun 1,2,3
通讯作者	Lin, Peijie
来源期刊	ELECTRONICS
EISSN	2079-9292
出版年	2020
卷号	9 期号:2
英文摘要	Improving the accuracy of very-short-term (VST) photovoltaic (PV) power generation prediction can effectively enhance the quality of operational scheduling of PV power plants, and provide a reference for PV maintenance and emergency response. In this paper, the effects of different meteorological factors on PV power generation as well as the degree of impact at different time periods are analyzed. Secondly, according to the characteristics of radiation coordinate, a simple radiation classification coordinate (RCC) method is proposed to classify and select similar time periods. Based on the characteristics of PV power time-series, the selected similar time period dataset (include power output and multivariate meteorological factors data) is reconstructed as the training dataset. Then, the long short-term memory (LSTM) recurrent neural network is applied as the learning network of the proposed model. The proposed model is tested on two independent PV systems from the Desert Knowledge Australia Solar Centre (DKASC) PV data. The proposed model achieving mean absolute percentage error of 2.74-7.25%, and according to four error metrics, the results show that the robustness and accuracy of the RCC-LSTM model are better than the other four comparison models.
英文关键词	photovoltaic power generation long short-term memory very short-term Power prediction similarity time period
类型	Article
语种	英语
国家	Peoples R China
开放获取类型	gold, Green Published
收录类别	SCI-E
WOS记录号	WOS:000518412200089
WOS关键词	RENEWABLE ENERGY ; NEURAL-NETWORKS ; HYBRID METHOD ; SOLAR ; GENERATION ; OUTPUT ; OPTIMIZATION ; SYSTEMS ; BENEFIT ; COST
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Physics, Applied
WOS研究方向	Computer Science ; Engineering ; Physics
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/314387
作者单位	1.Fuzhou Univ, Sch Phys & Informat Engn, Fuzhou 350108, Peoples R China; 2.Fuzhou Univ, Inst Micronano Devices & Solar Cells, Fuzhou 350108, Peoples R China; 3.Jiangsu Collaborat Innovat Ctr Photovolta Sci & E, Changzhou 21316, Jiangsu, Peoples R China
推荐引用方式 GB/T 7714	Chen, Biaowei,Lin, Peijie,Lai, Yunfeng,et al. Very-Short-Term Power Prediction for PV Power Plants Using a Simple and Effective RCC-LSTM Model Based on Short Term Multivariate Historical Datasets[J],2020,9(2).
APA	Chen, Biaowei,Lin, Peijie,Lai, Yunfeng,Cheng, Shuying,Chen, Zhicong,&Wu, Lijun.(2020).Very-Short-Term Power Prediction for PV Power Plants Using a Simple and Effective RCC-LSTM Model Based on Short Term Multivariate Historical Datasets.ELECTRONICS,9(2).
MLA	Chen, Biaowei,et al."Very-Short-Term Power Prediction for PV Power Plants Using a Simple and Effective RCC-LSTM Model Based on Short Term Multivariate Historical Datasets".ELECTRONICS 9.2(2020).