基于分段预测及天气相似日选择的区域电网短期负荷预测方法  

Short-Term Load Forecasting Method for Regional Power Grid Based on Segmented Prediction and Weather Similar Day Selection

作　　者：梁海维 王阳光 邓小亮 刘静 文明 于宗超 李文英 LIANG Haiwei;WANG Yangguang;DENG Xiaoliang;LIU Jing;WEN Ming;YU Zongchao;LI Wenying(State Grid Hunan Electric Power Company Limited Economic and Technological Research Institute,Changsha 410007,China;Hunan Key Laboratory of Energy Internet Supply-Demand and Operation,Changsha 410007,China;State Grid Hunan Electric Power Company Limited,Changsha 410004,China)

机构地区：[1]国网湖南省电力有限公司经济技术研究院,湖南长沙410007 [2]能源互联网供需运营湖南省重点实验室,湖南长沙410007 [3]国网湖南省电力有限公司,湖南长沙410004

出　　处：《湖南电力》2024年第5期109-116,共8页Hunan Electric Power

基　　金：国网湖南省电力有限公司科技项目(5216A2220014);湖南省科技创新平台与人才计划(2019TP1053)。

摘　　要：为了提高对低谷、午间高峰、午间低谷、晚间高峰时段的负荷预测精度,提出一种基于分段预测及天气相似日选择的短期负荷预测方法。首先,分析包括气象及经济在内的不同因素对区域电网不同时段负荷的影响,并选取相关特征构建训练集;其次,采用长短期记忆神经网络模型实现对不同时间点的负荷预测;之后,利用互信息及欧式距离选取与待预测日天气条件接近的相似日,并将该日负荷曲线作为参考,与前述分段负荷预测结果结合作为待预测日的负荷预测结果。实验结果表明,所提出的短期负荷预测方法能够有效提高短期负荷预测精度,特别是对低谷、午间高峰、午间低谷、晚间高峰时段的预测精度有明显提升。In order to improve the accuracy of load forecasting for the four key periods of power grid opera-tion,namely low valley load,noon peak load,waist load load,and evening peak load,a short-term load forecasting method based on segmented forecasting and weather similar day selection is proposed.Firstly,the paper analyzes the impact of different factors,including meteorological and economic factors,on the load of the regional power grid at different time periods,and select relevant features as the training set for construction.Secondly,the paper adopts a long short term memory neural network model to achieve load forecasting for different time periods.Using mutual information and Euclidean distance,the paper selects similar days with weather conditions close to the day to be predicted,and uses the load curve of that day as a reference,combining with the segmented load forecasting results as the load forecasting result for the day to be predicted.The experimental results show that the proposed short-term load forecasting method can effectively improve the accuracy of short-term load forecasting,especially for low valley,noon peak,waist load,and evening peak periods,with a significant improvement in prediction accuracy.

关 键 词：短期负荷预测 相似日选择 长短期记忆(LSTM) 神经网络 分段预测 

分 类 号：TM715.1[电气工程—电力系统及自动化]