AI-Driven Vehicle-to-Grid (V2G) in Smart Grids: A Theoretical Study
Author:
Open Access
- 26 August 2025
- journal article
- Published by EWA Publishing in Applied and Computational Engineering
- Vol. 180 (1) , 33-38
Abstract
With the rapid development of renewable energy such as solar and wind power, the matching of supply and demand in the power system faces greater challenges. Electric vehicles (EVs) provide distributed energy storage services such as peak and valley regulation and frequency regulation to the power grid through a two-way vehicle-to-grid (V2G) system, which improves the flexibility and stability of the power grid. This paper proposes a unified framework based on artificial intelligence (AI) that integrates load forecasting, battery health-aware reinforcement learning scheduling, dynamic pricing, and multi-agent collaborative control, aiming to achieve efficient V2G operation in large-scale smart grids. By reviewing relevant literature, this paper analyzes the potential of the framework in improving grid stability, reducing operating costs, promoting the use of renewable energy, and extending battery life, and explores key challenges such as battery degradation, network security, system interoperability, and regulatory complexity. The study points out that the current model is mainly based on theory and simulation, lacking the support of large-scale empirical data. In the future, it is necessary to combine actual operation data and pilot projects to improve battery aging modeling and user behavior differentiation analysis to promote the practical application and optimization of the framework.Keywords
This publication has 7 references indexed in Scilit:
- RETRACTED ARTICLE: Artificial intelligence-augmented smart grid architecture for cyber intrusion detection and mitigation in electric vehicle charging infrastructureScientific Reports, 2025
- Optimization of Electric Vehicle Charging and Discharging Strategies Considering Battery Health State: A Safe Reinforcement Learning ApproachWorld Electric Vehicle Journal, 2025
- Adaptive Multi-Agent Reinforcement Learning for Optimizing Dynamic Electric Vehicle Charging Networks in ThailandWorld Electric Vehicle Journal, 2024
- EnergAIze: Multi Agent Deep Deterministic Policy Gradient for Vehicle-to-Grid Energy Management2024
- Optimization Challenges in Vehicle-to-Grid (V2G) Systems and Artificial Intelligence Solving MethodsApplied Sciences, 2024
- An Insight of Deep Learning Based Demand Forecasting in Smart GridsSensors, 2023
- Network Security and Privacy Challenges in Smart Vehicle-to-GridIEEE Wireless Communications, 2017