Daily Power Load Curves Analysis Based on Grey Wolf Optimization Clustering Algorithm

摘要

When the fuzzy C-means clustering algorithm (FCM) is applied to solve the problem of daily load curve clustering analysis, its performance is usually affected by selection of the initial clustering center and the sample similarity is often characterized directly by distance of each samples, which causes clustering easy to fall into local optimum. In this paper, the daily load characteristic value index is used to deal with the data dimension reduction of the daily load curve and a fuzzy C-means clustering algorithm optimized by grey wolf optimizer (GWO-FCM) is proposed. GWO-FCM uses GWO to optimize the initial clustering center for FCM, which combines the global search capability of GWO and the local search capability of FCM The results shows that the proposed method can perform daily load curve clustering analysis effectively and obtain good robustness.