家庭电池储能系统在配电网中控制的机器学习与MPC方法比较

Abstract Control methods for Home Energy Management Systems implemented with traditional optimization techniques and state-of-the-art Machine Learning methods are presented and compared in this paper in the context of their impact on and interactions with Active Distribution Networks. Thus, model-based methods based on Model Predictive Control algorithms with different prediction qualities are first described and compared against model-free methods based on imitation learning and reinforcement learning. A practical, state-of-the-art, heuristic, rule-based controller is used as the baseline. An in-depth comparison is performed using metrics consisting of objective function values, grid constraint violations, and computational time. The results of applying these Home Energy Management Systems to a realistic German low voltage benchmark grid with 13 connected households, each containing solar generation, a battery storage system, and electrical loads are discussed. It is demonstrated that model-based and model-free methods can achieve improvements over typical rule-based methods, with varying performance in terms of objective function values and grid constraint violations depending on the forecasts, at the cost of higher computational complexity. Furthermore, model-free methods are shown to have in general low computational burden at higher objective function values with more grid constraint violations, with imitation-learning-based techniques proving to be the best compromise for practical applications.