Title: Smart grid short-term load estimation model based on BP neural network

Authors: Jianqiang Shi; Shi Chengchao; Han Lei; Xu Mengxi

Addresses: Electric Power Simulation and Control Engineering Centre of Nanjing Institute of Technology, Nanjing Jiangsu, 211167, China ' Xiangshui Yangtze River Wind Power Generation Co., Ltd., Yancheng Jiangsu 224600, China ' Electric Power Simulation and Control Engineering Centre of Nanjing Institute of Technology, Nanjing Jiangsu, 211167, China ' Electric Power Simulation and Control Engineering Centre of Nanjing Institute of Technology, Nanjing Jiangsu, 211167, China

Abstract: As reasonable short-term load estimation system can provide reliable support for the operating, planning and designing of the smart grid, in this paper, we propose an effective smart grid short-term load estimation method. Different types of data are input to the BP neural network and then the output of BP neural network is represented as the load estimation results. Although BP neural network can approximate any nonlinear continuous function with the condition of a specific structure and suitable weights, it is very difficult to obtain the global minimum result. In order to obtain the global optimum solution in short-term load estimation, we exploit the genetic algorithm to optimise the weights and thresholds of the BP neural network, which is the main advantage of the proposed model. Finally, experimental results demonstrate that the proposed method can estimate short-term load of smart grid with higher accuracy and it can also clearly show the load requirement distribution in different time period.

Keywords: smart grid; short-term load; BP neural network; genetic algorithm; model.

DOI: 10.1504/IJCSM.2020.106390

International Journal of Computing Science and Mathematics, 2020 Vol.11 No.2, pp.123 - 136

Received: 16 Aug 2017
Accepted: 25 Sep 2017

Published online: 31 Mar 2020 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article