The Power of Short - term Load Algorithm Based on LSTM. Issue 1 (March 2020)

• Record Type: Journal Article
• Authors: Wang, Zhankui; Wu, Junying; Xin, Rui; Bai, Tao; Zhao, Jianbin; Wei, Minglei; Li, Jingquan; Zhuang, Lei
• Is Part Of: IOP conference series. Volume 453:Issue 1(2020)
• Publication Date: 2020-03
• Subjects: LSTM -- influencing factors -- adam -- generalization -- short-term load.; Earth sciences -- Periodicals; Environmental sciences -- Congresses; Environmental sciences -- Periodicals; 550.5
• DOI: 10.1088/1755-1315/453/1/012056
• Languages: English
• ISSNs: 1755-1307

Abstract

Abstract: The power data is affected by many factors and has long time series, which fully meets the conditions of long-term and short-term memory neural network. This paper analyzes and models various influencing factors such as time, vacation and meteorology, and uses adaptive moment estimation optimization algorithm. The traditional optimization algorithm is improved, the generalization of the model is improved, and the short-term load forecasting of power can be stably and efficiently operated to ensure the reliability and safety of national electricity. In this paper, the short-term load forecasting experiment is carried out in a certain area of Hebei Province. The experimental results show that the proposed algorithm outperforms the existing similar model and has higher prediction accuracy.