基于改进回归模型的电网降温负荷预测  

Power Grid Cooling Load Forecast Based on Improved Regression Model

作　　者：张航 杨靖[1] 李昊霖 ZHANG Hang;YANG Jing;LI Hao-lin(School of Electrical Engineering,Guizhou University,Guiyang 550025,China)

机构地区：[1]贵州大学电气工程学院,贵州贵阳550025

出　　处：《控制工程》2023年第3期513-519,共7页Control Engineering of China

基　　金：国家自然科学基金资助项目(61861007,61640014);贵州省工业攻关项目(黔科合支撑[2019]2152);贵州省科技基金(黔科合基础[2020]1Y266);物联网理论与应用案例库(KCALK201708);贵州省农业攻关项目(黔科合支撑[2017]2520-1);贵州省教育厅创新群体(黔教合KY字[2021]012)。

摘　　要：随着科技的发展,人们的生活质量不断提高,与此同时对用电的需求也越来越高。空调等降温设备的大量使用,使降温负荷对电力系统安全经济运行的影响更加明显。以安阳市区配电网的历史负荷和气温数据为基础,利用灰色系统GM(1,1)模型预测出电网夏季的日基准负荷曲线。建立了日降温负荷与温度之间关系的一次回归模型、二次回归模型和分段回归模型,进行日降温负荷预测。考虑到温度累积效应的影响,对分段回归模型进行了修正和改进。经过验证优化后的模型进一步提高了预测精度,为准确预测夏季日高峰负荷提供了依据。Due to the development of science and technology,people’s quality of life is improving,meanwhile the demand for electricity is also increasing.With the extensive use of cooling equipment,such as air conditioners and cooling loads have more obvious impacts on the safe and economic operation of the power system.Based on the historical load and temperature data of Anyang urban distribution network,the gray system GM(1,1)model is used to predict the daily reference load curve of the power grid in summer.The primary regression model,secondary regression model,and segment regression model of the relationship between daily cooling load and temperature are established to predict daily cooling load.Considering the influence of the cumulative effect of temperature,the segmented regression model is modified and improved.The verified and optimized model further improves the prediction accuracy,and provides evidence for predicting accurately the peak load of the power grid in summer.

关 键 词：降温负荷 GM(1 1) 温度 回归模型 温度累积效应 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]