短期负荷预测中选择相似日的探讨  

Method to select similar days for short-term load forecasting

作　　者：莫维仁[1] 张伯明[1] 孙宏斌[1] 胡子珩[1] 

机构地区：[1]清华大学电机工程与应用电子技术系,北京100084

出　　处：《清华大学学报（自然科学版）》2004年第1期106-109,共4页Journal of Tsinghua University(Science and Technology)

基　　金：国家自然科学基金资助项目(50107005)

摘　　要：合理的选择预测相似日是提高负荷预测综合预测模型预测效果的有效途径。传统依据人工经验选择相似日并不具备最好的预测效果。为了进一步提高负荷预测准确度,该文深入研究了负荷的两个特征量,认为对预测日的负荷水平和负荷曲线形状进行预测时,应该选取不同的相似日,即该文提出的趋势相似日和形状相似日;给出了这两种相似日的选择方案,从日特征量、日前趋势相似度以及这两者的综合3个角度阐述了选择预测日的趋势相似日的原理和方法;该文通过应用实例证实了其中一个方案有效地提高了负荷预测准确度。Improved short-term load forecasting can be obtained by carefully selecting similar days in an integrated model for short-term load forecasting. Traditionally, similar days are selected based on experience, which can affect forecasting accuracy. Three methods were developed to classify trend-similar days from shape-similar days for short-term load forecasting in this paper. The three methods were compared to develop an effective forecasting method. Numerical tests verified the efficiency of the method.

关 键 词：电力系统规划 负荷预测 电力市场 综合模型 相似日 

分 类 号：TM715[电气工程—电力系统及自动化]