Home Electric Vehicle Charge Scheduling Using Machine Learning Technique

With the help of artificial intelligence and advanced metering infrastructure (AMI), the analysis of electric vehicle integration will play a vital role in the future smart grid. Because getting data from smart appliances, processing that data using advanced techniques to get the desired output in near real-time is going to be a significant advantage of the smart grid. In this paper, a machine learning technique called support vector machine(SVM) is used to analyze the home charge scheduling. With the help of user energy consumption, electric vehicle SOC information at different time intervals, it can predict the status of the electric vehicle, i.e., Idle, Grid to Vehicle(G2V), or Vehicle to Grid(V2G) with close to cent percent accuracy. The results show the advantage of the SVM technique for analysis of home charge scheduling using intermediate EV data.

I. Introduction

Nowadays, electric vehicles become an integral part of the modern transportation system in association with the future smart grid as the fossil fuel-based vehicle becomes the burden for the environment. But, a proper charging environment is required for the electric vehicle so that its impact on the distribution grid will be less in terms of many factors like stability and reliability of the smart grid [1]. In India, to adopt the electric vehicles, mainly three stakeholders, namely government, industry, and consumers, are coming forward to fulfill the vision 2030 [2]. However, to fulfill the said vision, there are many challenges. Among them, few are listed in Fig. 1.