Journal
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
Volume 19, Issue 5, Pages 6349-6363Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2022.3195701
Keywords
Optimal control; Mathematical models; Heuristic algorithms; Reinforcement learning; Training; Marine vehicles; Adaptation models; Deep reinforcement learning (DRL); optimal charging control; pulse power load; shipboard power system
Ask authors/readers for more resources
In this article, the charging control of the energy storage system for pulse power load accommodation in a shipboard integrated power system is studied. An improved twin-delayed deep deterministic policy gradient algorithm is proposed to solve this control problem. The proposed method addresses issues such as reward function design and constraint handling for control variables.
In this article, the charging control of the energy storage system for the pulse power load accommodation in a shipboard integrated power system (SIPS) is formulated as an optimal control problem. The SIPS is an input-affine nonlinear system with randomness and fast dynamics. The improved twin-delayed deep deterministic policy gradient algorithm -one of the deep reinforcement learning (DRL) algorithms, is proposed to solve this optimal control problem. The proposed DRL-based control solution considers the issues regarding the reward function design and input and ramp rate constraints handling for control variables. The proposed approach linked the optimal control and DRL framework. Test cases demonstrated that we could utilize DRL algorithms to control the nonlinear system with fast dynamics by following the specific reward function design, data sampling, and constraints handling techniques.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available