基于气象信息因素修正的灰色短期负荷预测模型.pdfVIP

第37 卷 第3 期 电 网 技 术 Vol. 37 No. 3 2013 年3 月 Power System Technology Mar. 2013 文章编号：1000-3673 （2013 ）03-0720-06 中图分类号：TM 715 文献标志码：A 学科分类号：470·4054 基于气象信息因素修正的灰色短期负荷预测模型 焦润海，苏辰隽，林碧英，莫瑞芳 （华北电力大学控制与计算机工程学院，北京市 昌平区 102206 ） Short-Term Load Forecasting by Grey Model With Weather Factor-Based Correction JIAO Runhai, SU Chenjun, LIN Biying, MO Ruifang (School of Control and Computer Engineering, North China Electric Power University, Changping District, Beijing 102206, China) ABSTRACT: To remedy the defects in applying grey model to 适用于含不确定因素的系统预测方法，比其他时间 short-term load forecasting, the multi-angle data organization 序列法精度更高，更适合解决各种情况下的短期电 strategy is improved. Choosing historical days with higher 力负荷预测问题。 similarity in social activity background as the similar days, a 短期负荷预测背景下的灰色模型改进可分为 criterion of abrupt change of weather factors is established to identify the abrupt change of weather factors in similar days, and 内部改进和外部改进两种方法。内部改进主要通过 the weather-sensitive load components in load data of similar 优化算法内部参数，提升规律挖掘能力。如文献[2] days are eliminated by regression method. The extrapolation of 中使用参数α 修正法修正背景值，使拟合得到的一 adjacent tendency and similar day substitution method are 阶微分方程更符合实际趋势发展情况；文献[3]选取 adopted to correct local distortion points, which are easy to 了更高次的GM(2,1)模型，使用三次样条函数和泰 appear during the forecasting by grey model. Experimental results show that using the improved grey model the load 勒逼近法计算衍生值与背景值，防止高阶灰色系统 forecasting accuracy can be evidently improved by one or two (grey system，GM)模型的变异问题。然而，对于存 percentage points in average a