Machine Learning-Based Charging Network Operation Service Platform Reservation Charging Service System

Abstract

This paper proposes a machine learning-based electric vehicle (EV) reserved charging service system, which takes into consideration the impacts from both the power system and transportation system. The proposed framework of charging network operation service platform links the power system with transportation system through the charging navigation of massive EVs. The "reserved charging + consumption" integrated service model would be great significant for dealing with large-scale integration of electric vehicles. It applies the concept of charging time window to optimization of EV charging prediction for the reserved charging service system, and designs a dynamic dispatching model based on sliding time axis to make charging process of users get rid of constraints of queuing time and charging service fee period.