Research on residential load classification method based on Multi-model parallel integration algorithm

Abstract

With the gradual upgrading of power grid to energy Internet, machine learning and artificial intelligence technology are booming in the field of load classification. In this paper, combined with the theory of artificial intelligence, aiming at the problem of residential user load type classification, a residential load classification algorithm based on multi model parallel integration(MMPI) is proposed. The algorithm constructs several base classifiers with different performance, embeds the ensemble learning load classification model, and processes them in parallel on MATLAB platform. An example is given to verify the effectiveness of the algorithm by using Irish electricity consumption data. The classification results show that, compared with the traditional single model load classification, the load classification method based on multi model parallel integration has higher classification accuracy and efficiency.