In the realm of urban transportation, metro systems serve as crucial and sustainable means of public transit. However, their substantial energy consumption poses a challenge to the goal of sustainability. Disturbances such as delays and passenger flow changes can further exacerbate this issue by negatively affecting energy efficiency in metro systems. To tackle this problem, we propose a policy-based reinforcement learning approach that reschedules the metro timetable and optimizes energy efficiency in metro systems under disturbances by adjusting the dwell time and cruise speed of trains. Our experiments conducted in a simulation environment demonstrate the superiority of our method over baseline methods, achieving a traction energy consumption reduction of up to 10.9% and an increase in regenerative braking energy utilization of up to 47.9%. This study provides an effective solution to the energy-saving problem of urban rail transit.

翻译：在城市交通领域中，地铁系统作为一种关键且可持续的公共交通工具发挥着重要作用。然而，其巨大的能源消耗对可持续发展目标构成了挑战。诸如延迟和客流变化等干扰因素会通过降低地铁系统的能效而进一步加剧这一问题。为解决该难题，我们提出了一种基于策略的强化学习方法，该方法通过调整列车的停站时间和巡航速度，在地铁系统遭遇干扰时重新编制运行图并优化能效。我们在仿真环境中开展的实验表明，该方法优于各类基线方法，实现了牵引能耗最高降低10.9%，再生制动能量利用率最高提升47.9%。本研究为城市轨道交通的节能问题提供了有效解决方案。