Ultra short term load forecasting for different types of industrial parks with intelligent buildings. Issue 1 (1st December 2022)

• Record Type: Journal Article
• Authors: Tang, Junci; Wang, Guanfu; Cai, Zhiyuan; Zhao, Xiaodong; Li, Haoyu; Cui, Jia; Li, Zihan
• Is Part Of: Journal of physics. Volume 2378 Issue 1(2022)
• Publication Date: 2022-12-01
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/2378/1/012082
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: For industrial parks with intelligent buildings, accurate forecasting of various load sizes may reduce the power supply pressure of the power grid. For industrial parks with intelligent buildings, considering the influence of weather factors and the dynamic electricity price game mechanism, the load forecasting of industrial parks often ignores the load of intelligent buildings and electric vehicles, resulting in insufficient satisfaction of residents in the buildings. The improved Attention-LSTM algorithm based on DBN structure is proposed. It takes into account the correlation between loads and the correlation between loads and energy sources. When forecasting high energy consumption industrial loads, the forecasting accuracy of intelligent building loads and electric vehicle loads is improved compared with the original algorithm, which ensures the satisfaction of residents in the building. Finally, an example is given to verify the advantages of the algorithm.