Electricity information big data based load curve clustering

Abstract

Clustering analysis of load curves on basis of electricity information big data is an important basis of load characterisitic and electricity consumption ha bits analysis of large users. In view of the slow speed of traditional K-means clustering algorithm in the background of big data, a parallel K-means clustering algorithm is proposed to speed up the clustering procedure. Firstly, all the load curves are de-noised by wavelet decomposing in order to reduce the influence of small fluctuations. Secondly, a multi-core parallel technology based K-means clustering algorithm is applied to load curve clustering. Thirdly, more than 40,000 load curves are clustered by the multi-core parallel technology based K-means clustering algorithm. Test results show that the proposed parallel K-means clustering algorithm can speed up clustering procedure effectively.