Abstract :

Global Electric Vehicle (EV) Sales Exceeded 17 Million Units In 2025, Representing Nearly One In Every Five New Vehicles Sold Worldwide, While The Transportation Sector Contributes Approximately 24% Of Global Energy-related CO₂ Emissions, Highlighting The Growing Demand For Sustainable Charging Infrastructures. The Increasing Penetration Of Renewable Energy Sources And The Rapid Deployment Of Fast EV Charging Stations Require Intelligent Power Management Systems Capable Of Maintaining Stable Operation Under Highly Dynamic Environmental And Loading Conditions. However, The Existing Artificial Neural Network With Model Predictive Control (ANN-MPC) Framework Suffers From High Computational Complexity, Slower Real-time Response, Limited Adaptability To Highly Nonlinear Renewable Energy Dynamics, And Increased Processing Overhead Caused By Continuous Predictive Optimization, Thereby Affecting DC Bus Voltage Regulation, Power-sharing Efficiency, And Battery Charging Performance. To Address These Limitations, This Paper Proposes A Deep Neural Network (DNN)- Based Intelligent Control Framework For A Renewable Energy-powered DC Microgrid Supporting Fast EV Charging. The Proposed Architecture Completely Replaces The ANN-MPC Controller With Distributed DNN Controllers That Directly Regulate The Fuel Cell, Wind Turbine, Solar Photovoltaic System, Battery Energy Storage System, And EV Charging Converter. The DNN Is Trained Offline Using Measured Operational Data And Subsequently Deployed For Real-time Converter Control, Enabling Rapid Nonlinear Decision-making Without Online Predictive Optimization. Consequently, The Proposed Framework Improves DC Bus Voltage Stability, Renewable Energy Utilization, Intelligent Battery Management, Charging Efficiency, Computational Performance, Scalability, And Overall Reliability, Making It Highly Suitable For Next-generation Sustainable Fast Electric Vehicle Charging Infrastructures.

Published:

25-7-2026

Issue:

Vol. 26 No. 7 (2026)

Page Nos:

1241-1253

Section:

Articles

License:

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

How to Cite