确定性合同分解中异常负荷数据的识别与修正

Load Outlier Identification and Correction for Deterministic Contract Decomposition

电力市场的合同分解中应用确定性电量分解算法需要制定典型负荷曲线,历史负荷中的异常数据必然影响典型负荷曲线的有效性。文中借鉴计算统计学的等高线图法,采用系统聚类方法构造谱系树,将样本映射到叶结点,提出一种新的负荷形状畸变识别方法,并将其与传统的t检验法相结合,应用于负荷异常数据的识别和修正。应用该方法对浙江电网的历史数据进行了异常负荷的识别和修正,分析结果说明其简单、有效。

In order to apply the deterministic contract decomposition algorithm to decompose contract energy, the typical load curve must be prepared. The abnormal historical load data can affect the validity of typical load curve. By referring to the contour map method of computational statistics, constructing the hierarchy tree based on hierarchical clustering method and mapping samples to the leaf nodes, a new load shape outlier identification method is proposed. The new method is combined with t test to identify and correct the load outlier. The historical data of power grid in Zhejiang Province is used to test the suggested approach and the result indicates that the algorithm is simple and effective.