摘要
电力系统历史负荷数据的准确与否对负荷预测效果有重要影响,首先采用减法聚类算法得到历史负荷数据的聚类数目和聚类中心,并以此来作为模糊c-均值聚类的起点,然后通过负荷曲线的横向相似性找出不良数据,最后修正不良数据,得到连续准确的负荷数据。通过实例分析验证了此方法的有效性。
The accuracy of the historical load data of the power system is of great importance to the power prediction. In this paper, first, the subtractive clustering algorithm is used to get the number of the clusterings and the cluster centers of the historical load data, which are used at the starting point of the Fuzzy c-means clustering. Second, the lateral similarity of the load curve is used to find out the negative data. Finally, the negative data is corrected using the characteristic curve to get the load data continuously and accurately. The validity of the method is verified through the actual case study.
出处
《电网与清洁能源》
北大核心
2017年第5期40-43,50,共5页
Power System and Clean Energy
基金
国家自然科学基金(51507134)~~
关键词
不良数据
减法聚类
模糊C-均值聚类
negative load data
subtractive clustering
fuzzy c-means clustering
