Multi-Stage Transmission Line Flow Control Using Centralized and Decentralized Reinforcement Learning Agents
This work addresses the labor-intensive process of power grid planning for engineers, though it is incremental as it applies existing RL methods to a specific domain.
The paper tackles the problem of automating bulk power system operational planning by introducing a multi-stage reinforcement learning approach that uses centralized and decentralized agents to regulate transmission line flows, achieving effective control in actual planning cases for SGCC Zhejiang Electric Power Company.
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.