Investigating Periodic Dependencies to Improve Short-Term Load Forecasting  

作　　者：Jialin Yu Xiaodi Zhang Qi Zhong Jian Feng 

机构地区：[1]State Grid Zhejiang Jiaxing Electric Power Co.,Ltd.,Jiaxing,314000,China [2]State Grid Zhejiang Electric Power Co.,Ltd.,Hangzhou,310000,China

出　　处：《Energy Engineering》2024年第3期789-806,共18页能源工程（英文）

基　　金：supported by Science and Technology Project of State Grid Zhejiang Corporation of China“Research on State Estimation and Risk Assessment Technology for New Power Distribution Networks for Widely Connected Distributed Energy”(5211JX22002D).

摘　　要：With a further increase in energy flexibility for customers,short-term load forecasting is essential to provide benchmarks for economic dispatch and real-time alerts in power grids.The electrical load series exhibit periodic patterns and share high associations with metrological data.However,current studies have merely focused on point-wise models and failed to sufficiently investigate the periodic patterns of load series,which hinders the further improvement of short-term load forecasting accuracy.Therefore,this paper improved Autoformer to extract the periodic patterns of load series and learn a representative feature from deep decomposition and reconstruction.In addition,a novel multi-factor attention mechanism was proposed to handle multi-source metrological and numerical weather prediction data and thus correct the forecasted electrical load.The paper also compared the proposed model with various competitive models.As the experimental results reveal,the proposed model outperforms the benchmark models and maintains stability on various types of load consumers.

关 键 词：Load forecasting transformer attention mechanism power grid 

分 类 号：TM714[电气工程—电力系统及自动化]