Adaptation of Renewable Energy Resources to Wireless EV Charging Using Deep Learning

Abstract

When it comes to realizing a safe, efficient, and dependable power supply. More lately, there has been a rise in the use of data-driven methods for modeling electric vehicle (EV) charging. Since this problem involves a lot of unknowns, researchers are trying to implement model-free solutions. Reinforcement learning (RL) is one of several model-free methods now in use, and has seen extensive use in EV charging control. RL is a method to machine learning that prioritizes optimizing for cumulative reward rather than individual rewards. Solar photovoltaic and wind energy both have the potential to be used in the future to generate electricity. The CDDQN technique is developed, which incorporates an act constraint into the DDQN system in order to address the charging issue with such restrictions. The CDDQN optimizes charging procedures to better predict Q values and reduce charging choosing action errors. Wind and solar energy are great options since they do not harm the environment. The layout of the charging circuit is created and evaluated in MATLAB Simulink, taking into account the changing recharging requirements of EVs. Additionally, this work explores the use of RL in EV coordinating to study and design state-of-the-art optimized EMSs that may be used for EV recharging.

Keywords:

• wireless EV charging
• renewable energy sources
• deep learning

Acknowledgment

There is no acknowledgement involved in this work.

Authorship contributions

All authors are contributed equally to this work.

Ethics approval and consent to participate

No participation of humans takes place in this implementation process.

Human and animal rights

No violation of Human and Animal Rights is involved.

Disclosure statement

The authors declare that they have no conflicts of interest to report regarding this study.

Data availability statement

Data sharing not applicable to this article as no datasets were generated or analyzed during this study.

Additional information

Funding

The authors received no specific funding for this study.

Notes on contributors

S. Balaji

S. Balaji, is currently working as Assistant professor in the Department of Electrical and Electronics Engineering at KCG College of Technology, Chennai. He received his B.E degree in Electrical and Electronics Engineering at SSN College of Engineering, Chennai and M.E Degree in Power Electronics and Drives at RMK Engineering College. He is currently pursuing his Ph.D degree at Anna University, Chennai, Tamil Nadu. His research interests are wireless inductive power transfer for electric vehicles and power converters for electric vehicles.

T. Anuradha

T. Anuradha, is currently working as the Professor and Head of the Department of Electrical and Electronics Engineering at KCG College of Technology, Chennai. She has completed her B.E degree in Electrical and Electronics Engineering at Alagappa Chettiar College of Engineering and Technology, Madurai Kamaraj University and M.E. Degree in Power Systems Engineering at College of Engineering, Guindy, Anna University, Chennai. She received her Ph.D degree in Faculty of Electrical Engineering from Anna University, Tamil Nadu State. She majorly focuses on developing eco-friendly, cost-effective, easily adaptable advanced power electronic interfaces for hybrid renewable energy systems for rural electrification projects and IOT, AI, ML based control techniques for Electric vehicle and smart grid applications. Her primary research interests are Renewable Energy Systems, Power Electronics and Drives, Smart Grids and Electric Vehicle Technologies.