Abstract

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.

Highlights

  • THE increasing pressure from environment protection has made it urgent to conduct the research on accommo‐Manuscript received: May 17, 2020; accepted: October 26, 2020

  • We focus on verifying the effectiveness and feasibility of the decentralized deep policy gradient (DDPG) algorithm with simulations in a modified IEEE 14-bus test system [32]

  • It is composed of two synchronous generators, one 2.5 MW inverterbased distributed generator (IBDG) installed at bus 14, twelve loads, and one load disturbance

Read more

Summary

INTRODUCTION

Manuscript received: May 17, 2020; accepted: October 26, 2020. Date of CrossCheck: October 26, 2020. The aforemen‐ tioned optimization-based approaches have made outstanding contributions to the design of control parameters for VSGs based on different requirements of power system stability. These approaches are built upon small-signal modeling approach with linearization procedure and simpli‐ fied mathematical model. It is difficult for engineers to analyze the im‐ pact of VSG on the power system stability and design the corresponding optimal control strategy with a variety of un‐ certain system disturbances.

SYSTEM MODEL AND PROBLEM FORMULATION
Objective
TRANSFORMATION AND SOLUTION
Formulation of Reinforcement Learning Task
DDPG Algorithm
Initialize a random disturbance for control behavior exploration
SIMULATION RESULTS
Training Neural Networks and Comparison
Load Disturbance
Performance Test in a New Test System
CONCLUSION
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call