发表机构
University of Massachusetts Amherst; Virginia Tech（马萨诸塞大学阿默斯特分校; 弗吉尼亚理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究最优输电切换问题，比较强化学习框架与基于混合整数线性规划的优化方法，通过在IEEE RTS-96 24节点系统上的案例研究发现，强化学习智能体在低预算下能产生接近最优解，生成可行解速度比优化求解器快两到三个数量级。
AI 中文摘要
最优输电切换（OTS）通过策略性地断开输电线路来降低发电成本，但其混合整数线性规划（MILP）公式在大规模输电网络中扩展性较差。强化学习（RL）提供了一种计算效率高的替代方法，但现有的基于RL的OTS方法依赖软惩罚，允许违反物理约束。本文对OTS的RL框架和基于MILP的优化方法进行了比较。在IEEE RTS-96 24节点系统上进行了案例研究；结果表明，智能体在低切换预算下能够产生接近最优的解决方案，在高切换预算下倾向于产生次优解决方案。然而，RL智能体生成可行解决方案的速度比优化求解器快两到三个数量级。
英文摘要
Optimal Transmission Switching (OTS) reduces generation cost by strategically opening transmission lines, but its mixed-integer linear program (MILP) formulation scales poorly for large-scale transmission networks. Reinforcement learning (RL) offers a computationally efficient alternative, but existing RL-based OTS approaches rely on soft penalties that permit physical constraint violations. This paper presents a comparison between an RL framework and an MILP-based optimization method for OTS. Case studies were carried out on the IEEE RTS-96 24-bus system; results show that the agent was able to produce near-optimal solutions at low switching budgets and tended to yield suboptimal solutions at high switching budgets. However, the RL agent was able to generate feasible solutions two-to-three orders of magnitude faster than the optimization solver.
