Reinforcement Learning for Electric Vehicle Applications in Electric Power Systems

• Grant number: 23/05708-3
• Support Opportunities: Scholarships in Brazil - Doctorate
• Effective date (Start): August 01, 2024
• Effective date (End): December 31, 2027
• Field of knowledge: Engineering - Electrical Engineering - Power Systems
• Principal Investigator: Marcos Julio Rider Flores
• Grantee: Lucas Zenichi Terada
• Host Institution: Faculdade de Engenharia Elétrica e de Computação (FEEC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 21/11380-5 - CPTEn - São Paulo Center for the Study of Energy Transition, AP.CCD

Abstract

The global increase in the adoption of Electric Vehicles (EVs) is recognized as a recent strategy to combat climate change due to its effectiveness in reducing greenhouse gas emissions and improving urban air quality. Simultaneously, Distributed Energy Resources (DERs), such as photovoltaic (PV) systems and battery energy storage systems (BESS), are increasingly prevalent in sustainable environments. This doctoral project aims to develop a robust and adaptable Reinforcement Learning (RL) model to efficiently manage energy in various electric power system scenarios, integrating EVs and DERs. Diverse scenarios will be explored, including smart homes, microgrids, and electrified parking lots, also encompassing public charging infrastructure managed by different agents, such as Charging Point Operators (CPO) and Electric Mobility Service Providers (eMSP). Through the use of advanced simulations and real data, the model will be applied and validated in both laboratory settings and real infrastructures, with the goal of developing solutions for intelligent EV charging, public charging price optimization, and fleet management. This study seeks to make contributions to the field of energy management, promoting sustainability and energy efficiency across various operational scenarios.