Abstract :

Hybrid Electric Vehicles (HEVs) Have Emerged As A Promising Solution For Reducing Fuel Consumption, Minimizing Greenhouse Gas Emissions, And Improving Overall Transportation Sustainability. However, Achieving Optimal Energy Management In HEVs Remains A Significant Challenge Due To The Dynamic Nature Of Driving Conditions, Battery State Variations, And Power Distribution Requirements Between Internal Combustion Engines And Electric Motors. Traditional Rule-based And Optimization-based Energy Management Strategies Often Struggle To Adapt Effectively To Complex And Uncertain Operating Environments. This Study Presents A Reinforcement Learning (RL)-Driven Energy Management System (EMS) Designed To Enhance The Performance, Efficiency, And Adaptability Of Hybrid Electric Vehicles. The Proposed Approach Employs An RL Agent That Continuously Learns Optimal Power-splitting Decisions Through Interaction With The Vehicle Environment, Considering Parameters Such As Battery State Of Charge (SoC), Vehicle Speed, Power Demand, And Driving Patterns. By Maximizing A Cumulative Reward Function That Balances Fuel Economy, Battery Health, And Emission Reduction, The RLbased EMS Dynamically Adapts To Varying Road And Traffic Conditions. Simulation Results Demonstrate That The Proposed Strategy Achieves Superior Fuel Efficiency, Reduced Energy Consumption, And Improved Battery Utilization Compared To Conventional Energy Management Techniques. Furthermore, The Learning-based Framework Exhibits Strong Adaptability To Different Driving Cycles Without Requiring Extensive Prior Knowledge Of Vehicle Operating Conditions. The Findings Indicate That Reinforcement Learning Offers A Robust And Intelligent Solution For Next-generation HEV Energy Management Systems, Contributing To Enhanced Vehicle Performance, Environmental Sustainability, And Operational Reliability.

Published:

15-11-2023

Issue:

Vol. 23 No. 11 (2023)

Page Nos:

299 - 307

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite