Multi-Stage Transmission Line Flow Control Using Centralized and Decentralized Reinforcement Learning Agents

TL;DR

This paper introduces a multi-stage reinforcement learning framework with centralized and decentralized agents to automate transmission line flow control, improving power grid operation efficiency and security.

Contribution

It presents a novel multi-stage RL approach combining centralized and decentralized agents for automated power grid flow control under normal and contingency conditions.

Findings

Effective control of transmission line flows demonstrated on real power grid cases.

Centralized SAC agent manages wide-area generator outputs.

Decentralized SAC agent handles local load adjustments.

Abstract

Planning future operational scenarios of bulk power systems that meet security and economic constraints typically requires intensive labor efforts in performing massive simulations. To automate this process and relieve engineers' burden, a novel multi-stage control approach is presented in this paper to train centralized and decentralized reinforcement learning agents that can automatically adjust grid controllers for regulating transmission line flows at normal condition and under contingencies. The power grid flow control problem is formulated as Markov Decision Process (MDP). At stage one, centralized soft actor-critic (SAC) agent is trained to control generator active power outputs in a wide area to control transmission line flows against specified security limits. If line overloading issues remain unresolved, stage two is used to train decentralized SAC agent via load throw-over at local substations. The effectiveness of the proposed approach is verified on a series of actual planning cases used for operating the power grid of SGCC Zhejiang Electric Power Company.