Reinforcement learning and A^(*)search for the unit commitment problem Patrick de Mars^(∗),Aidan O’Sullivan

作     者：Patrick de Mars Aidan O’Sullivan 

作者机构：UCL Energy InstituteUnited Kingdom 

出 版 物：《能源与人工智能(英文)》 (Energy and AI)

年 卷 期：2022年第9卷第3期

页      面：172-181页

学科分类：0401[教育学-教育学] 04[教育学] 

基　　金：supported by an Engineering and Physical Sciences Research Council research studentship(grant number:EP/R512400/1) 

主　　题：Unit commitment Reinforcement learning Tree search Power systems 

摘      要：Previous research has combined model-free reinforcement learning with model-based tree search methodsto solve the unit commitment problem with stochastic demand and renewables generation. This approachwas limited to shallow search depths and suffered from significant variability in run time across probleminstances with varying complexity. To mitigate these issues, we extend this methodology to more advancedsearch algorithms based on A^(*) search. First, we develop a problem-specific heuristic based on priority list unitcommitment methods and apply this in Guided A^(*) search, reducing run time by up to 94% with negligibleimpact on operating costs. In addition, we address the run time variability issue by employing a novel anytimealgorithm, Guided IDA^(*), replacing the fixed search depth parameter with a time budget constraint. We showthat Guided IDA^(*) mitigates the run time variability of previous guided tree search algorithms and enablesfurther operating cost reductions of up to 1%.