Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Reinforcement Learning for Vehicle-to-Grid Voltage Regulation: Single-Hub to Multi-Hub Coordination with Battery-Aware Constraints

Jingbo Wang, Roshni Anna Jacob, Harshal D. Kaushik, Jie Zhang

TL;DR

An intelligent control strategy based on the soft actor-critic algorithm is developed for voltage regulation through single and multi-hub charging systems while respecting realistic fleet constraints, demonstrating the viability of constraint-aware learning for critical grid services.

Abstract

This paper presents a Vehicle-to-Grid (V2G) coordination framework using reinforcement learning (RL). {An intelligent control strategy based on the soft actor-critic algorithm is developed for voltage regulation through single and multi-hub charging systems while respecting realistic fleet constraints. A two-phase training approach integrates stability-focused learning with battery-aware deployment to ensure practical feasibility. Simulation studies on the IEEE 34-bus system validate the framework against a standard Volt-Var/Volt-Watt droop controller. Results indicate that the RL agent achieves performance comparable to the baseline control strategy in nominal scenarios. Under aggressive overloading, it provides robust voltage recovery (within 10% of the baseline) while prioritizing fleet availability and state-of-charge preservation, demonstrating the viability of constraint-aware learning for critical grid services.}

Reinforcement Learning for Vehicle-to-Grid Voltage Regulation: Single-Hub to Multi-Hub Coordination with Battery-Aware Constraints

TL;DR

An intelligent control strategy based on the soft actor-critic algorithm is developed for voltage regulation through single and multi-hub charging systems while respecting realistic fleet constraints, demonstrating the viability of constraint-aware learning for critical grid services.

Abstract

This paper presents a Vehicle-to-Grid (V2G) coordination framework using reinforcement learning (RL). {An intelligent control strategy based on the soft actor-critic algorithm is developed for voltage regulation through single and multi-hub charging systems while respecting realistic fleet constraints. A two-phase training approach integrates stability-focused learning with battery-aware deployment to ensure practical feasibility. Simulation studies on the IEEE 34-bus system validate the framework against a standard Volt-Var/Volt-Watt droop controller. Results indicate that the RL agent achieves performance comparable to the baseline control strategy in nominal scenarios. Under aggressive overloading, it provides robust voltage recovery (within 10% of the baseline) while prioritizing fleet availability and state-of-charge preservation, demonstrating the viability of constraint-aware learning for critical grid services.}
Paper Structure (21 sections, 10 equations, 4 figures, 2 tables)

This paper contains 21 sections, 10 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. System Overview and Hub Model
  4. EV Fleet Model and Operational Constraints
  5. Battery Power Constraints
  6. SOC and SOH Evolution
  7. Fleet-Level Power Allocation
  8. Reinforcement Learning Framework
  9. State and Action Spaces
  10. Reward Function
  11. SAC Algorithm
  12. Training and Deployment Workflow
  13. Case Study
  14. Simulation Environment
  15. Control Algorithms
  16. ...and 6 more sections

Figures (4)

  • Figure 1: Learning architecture and training-deployment workflow for V2G voltage regulation control.
  • Figure 2: Evaluation Profiles. The left axis displays the time-varying load multipliers for both the Mild (peak $\lambda=1.5$) and Aggressive (peak $\lambda=3.0$) scenarios. The right axis indicates the corresponding EV fleet participation rate during the active V2G window (06:00--23:00).
  • Figure 3: Single-Hub Voltage Regulation Performance. (a)–(b) Mean feeder voltage profiles and improvements under mild and aggressive loading. (c) Fleet-average SOC. (d) Participating EV count. Voltages are averaged across all buses.
  • Figure 4: Multi-Hub Voltage Regulation. (a) Mild loading and (b) aggressive loading scenarios under coordinated V2G control. Subplots show mean voltages averaged across all network buses, illustrating feeder-wide voltage response relative to the baseline.