Journal
JOURNAL OF MODERN POWER SYSTEMS AND CLEAN ENERGY
Volume 9, Issue 4, Pages 919-929Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.35833/MPCE.2020.000267
Keywords
Power system stability; Optimal control; Adaptation models; Stability analysis; Reinforcement learning; Mathematical model; Damping; Adaptive control; virtual synchronous generator (VSG); reinforcement learning; deep learning
Categories
Funding
- U.S. National Science Foundation [1711951]
- Directorate For Engineering
- Div Of Electrical, Commun & Cyber Sys [1711951] Funding Source: National Science Foundation
Ask authors/readers for more resources
This paper presents a data-driven optimal control strategy for virtual synchronous generator (VSG) using reinforcement learning to achieve optimal adaptive control. The reward mechanism is designed to quantify control targets, and a decentralized deep policy gradient algorithm is employed to optimize the control policy.
This paper aims at developing a data-driven optimal control strategy for virtual synchronous generator (VSG) in the scenario where no expert knowledge or requirement for system model is available. Firstly, the optimal and adaptive control problem for VSG is transformed into a reinforcement learning task. Specifically, the control variables, i.e., virtual inertia and damping factor, are defined as the actions. Meanwhile, the active power output, angular frequency and its derivative are considered as the observations. Moreover, the reward mechanism is designed based on three preset characteristic functions to quantify the control targets: (1) maintaining the deviation of angular frequency within special limits; (2) preserving well-damped oscillations for both the angular frequency and active power output; (3) obtaining slow frequency drop in the transient process. Next, to maximize the cumulative rewards, a decentralized deep policy gradient algorithm, which features model-free and faster convergence, is developed and employed to find the optimal control policy. With this effort, a data-driven adaptive VSG controller can be obtained. By using the proposed controller, the inverter-based distributed generator can adaptively adjust its control variables based on current observations to fulfill the expected targets in model-free fashion. Finally, simulation results validate the feasibility and effectiveness of the proposed approach.
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