DeepOPF-AL:求解多载荷-解映射的AC-OPF问题的增强学习算法
DeepOPF-AL: Augmented Learning for Solving AC-OPF Problems with Multiple Load-Solution Mappings
摘要:
非凸AC-OPF问题存在多个负载-解映射,这对深度神经网络(DNN)算法提出了根本性的挑战。由于训练数据集可能包含对应于不同负载-解决方案映射的数据点的混合,DNN可能无法学习合法映射并生成劣质解决方案。我们提出DeepOPF-AL作为解决这个问题的增强学习方法。这个想法是训练DNN从增强输入中学习唯一的映射,即,(load初始点),到由迭代OPF求解器以负载和初始点作为摄入量生成的解。然后,我们将学习的增广映射应用于解决AC-OPF问题,比传统的求解器快得多。IEEE测试用例的仿真结果表明,与最近的DNN方案相比,DeepOPF-AL实现了明显更好的最优性和相似的可行性和加速性能,具有相同的DNN大小,但提高了训练复杂度。
英文摘要:
The existence of multiple load-solution mappings of non-convex AC-OPF problems poses a fundamental challenge to deep neural network (DNN) schemes. As the training dataset may contain a mixture of data points corresponding to different load-solution mappings, the DNN can fail to learn a legitimate mapping and generate inferior solutions. We propose DeepOPF-AL as an augmented-learning approach to tackle this issue. The idea is to train a DNN to learn a unique mapping from an augmented input, i.e., (load, initial point), to the solution generated by an iterative OPF solver with the load and initial point as intake. We then apply the learned augmented mapping to solve AC-OPF problems much faster than conventional solvers. Simulation results over IEEE test cases show that DeepOPF-AL achieves noticeably better optimality and similar feasibility and speedup performance, as compared to a recent DNN scheme, with the same DNN size yet elevated training complexity.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。