Research of Power User Load Classification Method Based on K-means and FSVM
Sun RongQi, Xiao XueQuan, Feng Zhou, Yushan Zhou · 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) · 2019
In order to realize the differentiation and refinement management of power users, the paper proposes a power user load classification method based on k-means and FSVM. The method takes the power use daily load curve index as the original sample, extracts the typical industry category by k-means clustering algorithm, combines the FSVM classification algorithm to train and test the samples of the known industry labels, and obtains the FSVM classification model of power user load. The simulation experiments show that the power user load classification model implemented by this method has higher classification accuracy and can effectively identify users in unknown industries.