A Reinforcement Learning Embedded Surrogate Lagrangian Relaxation Method for Fast Solving Unit Commitment Problems

Unit commitment problems are operation optimization problems solved by independent system operators (ISOs). These problems generally need to be solved within a limited time, and the quality of the solution can significantly impact the benefit of the power system. Due to the combinatorial complexities, quickly solving large-scale UC problems is particularly challenging and proposing an efficient solution methodology is crucial. In this paper, to accelerate solving speed, we embed reinforcement learning (RL) within the surrogate Lagrangian relaxation (SLR) framework. This approach leverages decomposition and machine learning to reduce the complexity of solving UC problems. By relaxing coupling constraints, the entire problem is decomposed into a set of sub-problems, each associated with a unit and significantly reduced in complexity. These sub-problems are then novelly formulated as Markov decision processes (MDPs), and a novel RL algorithm is used to rapidly generate high-quality feasible solutions. Our method substantially improves the overall speed of SLR and is applicable for solving large-scale UC problems. Numerical experiments on the IEEE 118-bus system and the 10K-bus system demonstrate that our method can obtain near-optimal solutions with no more than 3% performance degradation while achieving a speedup of 25$\sim$110 times compared to Gurobi, the state-of-the-practice solver.