A novel short-term load forecasting method based on mini-batch stochastic gradient descent regression model

doi:10.1016/j.epsr.2022.108226

	A novel short-term load forecasting method based on mini-batch stochastic gradient descent regression model
	Lizhen, Wu; Yifan, Zhao; Gang, Wang; Xiaohong, Hao
刊名	Electric Power Systems Research
	2022-10-01
卷号	211
关键词	Batch data processing Big data Electric power plant loads Forecasting Gradient methods K-means clustering Regression analysis Stochastic models Big data analyze Distributed parallel computing Load forecasting Map-reduce Map-reduce framework Mini-batch stochastic gradient descent Regression modelling Short term load forecasting Stochastic gradient descent Stochastic gradient descent algorithm
ISSN号	0378-7796
DOI	10.1016/j.epsr.2022.108226
英文摘要	Short-term Load Forecasting (STLF) is the basis of smart distribution network system operation, planning, and dispatching. The traditional linear regression prediction method has the problems of slow prediction speed and low prediction accuracy. In order to solve the problem, an improved regression model based on mini-batch stochastic gradient descent is proposed in this paper. Combined with the big data analysis and processing platform, the collected data is conformed, and the parallel computing model Map-Reduce is used to parallelize mini-batch stochastic gradient descent algorithm for improving the processing ability of mini-batch stochastic gradient descent algorithm in big data load forecasting, and shorten load forecasting time. Meanwhile, in order to clean up the duplicated data and bad data generated by the smart meter and sensor before calculation, an adaptive sorted neighborhood method is proposed to detect the repeatedly recorded data, and the K-means clustering method is used to eliminate the noise data.The experimental results show that the parallelized mini-batch stochastic gradient descent algorithm is much faster than the traditional regression analysis algorithm when the data volume is large. The average absolute percentage error of the load forecasting model for Belgium and a transformer station in Baiyin city of Gansu Province in China is 1.902% and 2.058% respectively, which satisfies the requirements of load forecasting. © 2022 Elsevier B.V.
WOS研究方向	Engineering
语种	英语
出版者	Elsevier Ltd
WOS记录号	WOS:000828167800009
内容类型	期刊论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/159080]
专题	电气工程与信息工程学院
作者单位	College of Electrical and Information Engineering, Lanzhou University of Technology, Gansu, Lanzhou; 730050, China
推荐引用方式 GB/T 7714	Lizhen, Wu,Yifan, Zhao,Gang, Wang,et al. A novel short-term load forecasting method based on mini-batch stochastic gradient descent regression model[J]. Electric Power Systems Research,2022,211.
APA	Lizhen, Wu,Yifan, Zhao,Gang, Wang,&Xiaohong, Hao.(2022).A novel short-term load forecasting method based on mini-batch stochastic gradient descent regression model.Electric Power Systems Research,211.
MLA	Lizhen, Wu,et al."A novel short-term load forecasting method based on mini-batch stochastic gradient descent regression model".Electric Power Systems Research 211(2022).