Bi-level Off-policy Reinforcement Learning for Volt/VAR Control Involving Continuous and Discrete Devices
This addresses the challenge of model-free coordination for power grid control, offering a solution for utility operators, though it appears incremental as it builds on existing RL techniques for a specific domain.
The paper tackles the Volt/Var control problem in active distribution networks by coordinating slow and fast timescale devices, proposing a bi-level off-policy reinforcement learning algorithm that achieves stable optimization without model information and outperforms existing methods.
In Volt/Var control (VVC) of active distribution networks(ADNs), both slow timescale discrete devices (STDDs) and fast timescale continuous devices (FTCDs) are involved. The STDDs such as on-load tap changers (OLTC) and FTCDs such as distributed generators should be coordinated in time sequence. Such VCC is formulated as a two-timescale optimization problem to jointly optimize FTCDs and STDDs in ADNs. Traditional optimization methods are heavily based on accurate models of the system, but sometimes impractical because of their unaffordable effort on modelling. In this paper, a novel bi-level off-policy reinforcement learning (RL) algorithm is proposed to solve this problem in a model-free manner. A Bi-level Markov decision process (BMDP) is defined to describe the two-timescale VVC problem and separate agents are set up for the slow and fast timescale sub-problems. For the fast timescale sub-problem, we adopt an off-policy RL method soft actor-critic with high sample efficiency. For the slow one, we develop an off-policy multi-discrete soft actor-critic (MDSAC) algorithm to address the curse of dimensionality with various STDDs. To mitigate the non-stationary issue existing the two agents' learning processes, we propose a multi-timescale off-policy correction (MTOPC) method by adopting importance sampling technique. Comprehensive numerical studies not only demonstrate that the proposed method can achieve stable and satisfactory optimization of both STDDs and FTCDs without any model information, but also support that the proposed method outperforms existing two-timescale VVC methods.