Nonintrusive Monitoring for Electric Vehicles Based on Zero-Shot Learning

Abstract

Monitoring the charging behavior of electric vehicle clusters will contribute to developing more effective energy management strategies for grid operators. A low implementation cost leads to a wide application prospect in nonintrusive monitoring for EVs. Aiming at the problem that traditional nonintrusive monitoring methods cannot identify unknown devices accurately due to the lack of classes, a nonintrusive monitoring method based on zero-shot learning (ZSL) is proposed in this article, one which can monitor the unknown types of EVs connected to charging piles. First, the charging characteristics of known EVs and unknown EVs are extracted by dictionary learning. Then EVs are classified by ZSL based on sparse coding. Furthermore, EVs are decomposed based on the proposed multimode factorial hidden Markov model (FHMM). Finally, the EV dataset of Pecan Street is used to verify the effectiveness and accuracy of the proposed method.