基于多气象因素混合回归的重庆地区夏季日最高负荷预测  

Summer Daily Maximum Load Forecasting in Chongqing Based on Mixed Regression of Multiple Meteorological Factors

作　　者：刘德旭 刘艳 潘永旗 罗锡斌 黄炜斌[1,2] 马光文[1,2] LIU De-xu;LIU Yan;PAN Yong-qi;LUO Xi-bin;HUANG Wei-bin;MA Guang-wen(College of Water Resource and Hydropower,Sichuan University,Chengdu 610065,China;State Key Laboratory of Hydraulics and Mountain River Engineering,Sichuan University,Chengdu 610065,China;State Grid Chongqing Electric Power Company,Chongqing 400014,China)

机构地区：[1]四川大学水利水电学院,四川成都610065 [2]四川大学水力学与山区河流开发保护国家重点实验室,四川成都610065 [3]国网重庆市电力公司,重庆400014

出　　处：《水电能源科学》2020年第4期185-188,共4页Water Resources and Power

基　　金：国网重庆市电力公司科技项目(2019渝电科技15#)。

摘　　要：鉴于利用短期负荷对气象的响应进行负荷预测能部分反映负荷形成的物理机制,基于主要气象因子与负荷的强相关性,采用混合回归方法模拟不同星期类型日最高负荷,并考虑积温效应和降雨对负荷的特殊影响,建立相应的修正函数对模拟结果进行修正,从而得到完整的能用于短期日最高负荷预测的多气象因素混合回归模型。对重庆地区日最高负荷的模拟与预测结果表明,率定期模拟平均误差为4.35%,在积温效应和降雨修正后,平均误差分别降至4.19%、4.01%;率定好的模型预测平均误差为1.99%,验证了模型具有可靠性和有效性。In view of the fact that short-term load forecasting based weather response can partly reflect the physical mechanism of load formation,based on the strong correlation between main meteorological factors and load,the mixed regression method is used to simulate the daily maximum load of different week types.The accumulated temperature effect and the special influence of rainfall on load are taken into account,and the corresponding correction function is established to modify the simulation results.Thus,a mixed regression model of multi-meteorological factors is obtained to predict short-term daily maximum load.The simulation and prediction results of the daily maximum load in Chongqing show that the average error of periodic simulation is 4.35%.After the accumulated temperature effect and rainfall correction,the average error is reduced to 4.19%and 4.01%,respectively.The average prediction error of the calibrated model is 1.99%,which verifies the reliability and effectiveness of the model.

关 键 词：电力负荷预测 气象因素 混合回归 重庆地区 

分 类 号：TM715[电气工程—电力系统及自动化]