.png){kind=icon}
.png){kind=icon}
Return
Protection and Coordination Control Strategy Using Deep Deterministic Policy Gradient for Passive Hybrid Energy Storage Systems
.png){kind=icon}
PRE
AI
K
M
A
S
P
DOI：10.1002/est2.70436.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The increasing integration of photovoltaic (PV) sources for electric vehicle (EV) charging necessitates advanced energy management strategies that reduce grid dependency while ensuring safe and efficient operation of hybrid energy storage systems (HESSs). Passive battery–supercapacitor topologies offer advantages in terms of simplicity, cost, and efficiency. However, their practical deployment is constrained by limited controllability, power oscillations, and inadequate protection under dynamic operating conditions. This study proposes a protection-aware deep deterministic policy gradient-based power coordination framework for a PV-integrated passive HESS–EV system with grid interaction. The proposed controller enhances the operational flexibility of the passive topology by intelligently coordinating power flow among the PV source, battery, supercapacitor, and grid while simultaneously enforcing protection against overcharging and undercharging. The actor–critic architecture enables continuous double-evaluation of control actions, effectively suppressing voltage and power oscillations and preventing abnormal power flow directions. Comprehensive studies incorporating multiple coordination control strategies, followed by real-time validation on an edge-based embedded platform, demonstrate the practical feasibility of the proposed approach. The findings of the study highlight a significant improvement in system effectiveness under the PV-only operating conditions, rising from 57.495% without any control to 66.667% with conventional Stateflow-based logic, and further to 97.278% with the proposed DDPG controller. The experimental results closely align with the desired power coordination outcomes, achieving 96.348% effectiveness on the edge-based embedded platform. These findings confirm that the proposed DDPG-based approaches certain operational characteristics typically associated with active topologies, including improved power coordination and oscillation suppression, while preserving the simplicity and cost advantages of passive HESS, making it a promising solution for next-generation PV-assisted EV charging systems.
Keywords:
deep deterministic policy gradient control
passive topology
protection and power coordination control
PV-connected systems
Journal
E
IF:
4
Papers:
984
Citations:
2.2K
Organization
Cited Papers