基于气象灵敏度分析和特征日修正的短期日负荷曲线预测  

Short Term Daily Load Forecasting Based on Meteorological Sensitivity Analysis and Typical Day Correction

作　　者：覃芳璐 李滨[2] 吴茵 QIN Fanglu;LI Bin;WU Yin(Power Dispatching Control Center,Guangxi Power Grid,Guangxi Nanning 530023,China;Key Laboratory of Guangxi Electric Power System Optimization and Energy Saving Technology,Guangxi University,Nanning 530004,China)

机构地区：[1]广西电网电力调度控制中心,广西南宁530023 [2]广西电力系统最优化与节能技术重点实验室(广西大学),广西南宁530004

出　　处：《广西电力》2018年第3期10-16,共7页Guangxi Electric Power

摘　　要：短期负荷预测是电力系统运行的基础工作,准确的负荷预测是系统安全稳定运行的重要保障。随着电力市场的不断扩张,气象敏感负荷在负荷总体中所占比例急剧上升,气象成为电力调度部门在制定运行计划时不可忽略的重要因素。提出了一种基于气象灵敏度分析和特征日修正的短期日负荷曲线预测方法,研究季节性气象与负荷的相关性,提取关键气象因素建立回归拟合模型,通过函数求导法得到负荷与关键气象因子的灵敏度;由气象特征判别函数找到待预测日的气象特征日与趋势特征日,结合日负荷极值预测值计算得预测日负荷曲线。最后通过采用我国南方某地区的负荷实际数据,验证了所提方法的准确性和有效性。Short-term load forecasting is the basic work in power system operation. Accurate load forecasting is an important guarantee for the system＇s security and stability operation. Along with the continuous expansion of the electricity market, weathersensitive load has a sharp rising proportion in the whole load. Meteorology becomes an important factor that cannot be ignored in the operation plan making of power dispatching department. A short term daily load forecasting method based on meteorological sensitivity and typical day correction is proposed. The correlation between load and seasonal meteorology is studied, and key meteorological factors are extracted to build up regression model. Function derivation method is used to get the sensitivity between load and key meteorological factor. Meteorological feature discriminant function is used to find the typical meteorological day and typical tendency day of the forecasting day. The load curve of forecasting day is calculated combining with extreme value and prediction value of daily load. Finally the actual load data of a certain region in the South China is used to testify the accuracy and validity of proposed method.

关 键 词：短期负荷预测 气象因素 灵敏度 气象特征日 

分 类 号：TM715[电气工程—电力系统及自动化]