Adaptive Charging Strategy for Electric Vehicle Based on Multiagent Reinforcement Learning

  • 李 憲龍

Student thesis: Doctoral Thesis

Abstract

The electric vehicle (EV) is innovative and presents immense promise for the automotive industry in terms of greenhouse emission reduction and the replacement of internal combustion vehicles Owing to the unique charging requirements and EV characteristics the driver of an EV faces significant issues on a daily basis such as determining a charging strategy based on minimizing charging costs or waiting time while exploring EV charging stations (CSs) This thesis presents an adaptive charging strategy model that implements the EV in a manner so as to challenge the uncertainty of a CS in terms of the price or popularity rate which are unknown but can be determined in the query time A Multiagent Reinforcement Learning model is employed to acquire information from the EV consumption log and information regarding the CS for formulating a charging strategy based on cost and time efficiency Furthermore characteristics and constraints such as battery charging and end-of-day energy requirements are considered The proposed model adapts to uncertainties when making charging decisions regarding preferable CSs at planned periods if necessary It demonstrates an adaptive charging strategy considering cost or time and consuming requirements with a simulation using real-world data Four extreme conditions are tested to verify the robustness and adaptivity of the model
Date of Award2020
Original languageEnglish
SupervisorHong-Tzer Yang (Supervisor)

Cite this

'