面向新型电力系统的多决策单元短期负荷统一预测  

Global Short-Term Load Forecasting for Multi Decision Making Units in the New Power System

作　　者：王兆华[1,2] 李通 王博[1,2] 张斌 赵文辉[1,2] WANG Zhaohua;LI Tong;WANG Bo;ZHANG Bin;ZHAO Wenhui(School of Management and Economics,Beijing Institute of Technology,Beijing 100081,China;Center for Sustainable Development&Intelligent Decision Making,Beijing Institute of Technology,Beijing 100081,China)

机构地区：[1]北京理工大学管理与经济学院,北京100081 [2]北京理工大学可持续发展与智能决策研究中心,北京100081

出　　处：《计量经济学报》2022年第1期106-125,共20页China Journal of Econometrics

基　　金：国家自然科学基金(72141302,72074026,71804010,91746208,71573016,71774014,72174023);国家杰出青年科学基金(71625003);教育部哲学社会科学研究重大课题攻关项目(21JZD027);北京市社会科学基金(20JCC108,21GLC057);北京市自然科学基金(9212016)。

摘　　要：短期负荷精准预测,是保证新型电力系统安全稳定运行的关键技术之一.然而,居民负荷预测面临着用户量巨大、负荷高异质性、高波动性和高随机性的难点,随着用户类型和数据的增加,会导致模型复杂度大幅上升,难以满足新型电力系统中负荷预测的要求.为此,本文构建了基于预测导向自编码器的结构化长短时神经网络模型,通过单一模型实现对所有类型用户短期负荷的精准预测.与同类模型相比,本文提出的13种组合模型预测精度提高7.16%~11.59%,同时对非电力领域的高异质性主体复杂高频时间序列的统一预测也有一定的借鉴意义.Accurate short-term load forecasting is one of the key technologies to ensure the safe and stable operation of new power systems.However,residential load forecasting faces the difficulties of huge number of users,high load heterogeneity,high volatility and high randomness.With the increase of user types and data,the complexity of the model will increase significantly,making it difficult to meet the requirements of load forecasting in new power systems.Therefore,this paper develops a structured long-and short-term neural network model based on prediction-oriented autoencoders,which can accurately forecast the short-term load of all types of users through a single model.Compared with similar models,the prediction accuracy of the 13 combined models proposed in this paper is improved by 7.16%~11.59%,and it is also of great referential significance for the unified prediction of complex high-frequency time series of highly heterogeneous subjects in non-electricity fields.

关 键 词：居民电力消费行为 短期负荷精准预测 深度学习 全局预测 

分 类 号：TM715[电气工程—电力系统及自动化] TP183[自动化与计算机技术—控制理论与控制工程]