目的 为应对极端高温天气对电力系统供需平衡造成的冲击，提出一种面向中长期的电力系统韧性提升方法。 方法 首先，模拟持续性极端高温场景下“源-荷”耦合出力特性，并利用时序运行模拟模型对系统韧性表现进行初评估；其次，基于运行模拟结果，在电力供需平衡的基础上以供电成本与负荷削减成本之和最小为目标，建立面向韧性提升的电力资源规划模型，得到韧性提升组合措施；最后，对韧性提升策略场景进行运行模拟，以验证其有效性。 结果 以2025年广东省为案例场景，与未实施电力系统韧性提升策略的场景相比，实施策略后极端高温天气下系统累积缺供电量、最大失负荷规模和因电力短缺而造成的经济损失分别降低了86.71%、60.72%和91.55%，系统最小供电水平提升了11.07%。 结论 通过协同供电资源扩容与负荷资源部署，电力系统韧性提升策略有效地提升了极端高温天气下系统的供电能力，同时降低了因电力短缺而造成的经济损失和社会代价。

Objectives To address the impact of extreme high-temperature weather on the supply and demand balance of power systems, a medium- to long-term method for enhancing power system resilience is proposed. Methods First, the coupled “source-load” output characteristics under sustained extreme high-temperature scenarios are simulated, and an initial evaluation of system resilience is performed using a chronological operation simulation model. Second, based on the operation simulation results, a resilience enhancement-oriented power resource planning model is established, with the objective of minimizing the combined cost of power supply and load shedding under the constraint of supply and demand balance, thereby deriving combined measures for resilience enhancement. Finally, operation simulations of the resilience enhancement strategy scenarios are conducted to verify their effectiveness. Results Taking Guangdong Province in 2025 as a case study, compared with the scenario without the implementation of the resilience enhancement strategies for power systems, the application of such strategies under extreme high-temperature weather decreases the cumulative power shortage, maximum lost load scale, and economic losses caused by power shortage by 86.71%, 60.72%, and 91.55%, respectively. The system’s minimum power supply level increases by 11.07%. Conclusions By coordinating the expansion of power supply resources and deployment of load resources, the resilience enhancement strategies effectively improve the power system’s supply capacity under extreme high-temperature weather, while reducing the economic loss and social cost caused by power shortages.

灾后故障配电网的应急抢修及重构需求，面临着灾情的不确定性、多抢修队调配特性、抢修与重构耦合等多个挑战。本文基于强化学习构建了灾后多抢修队的抢修调配模型，设计了状态粗筛机制以固定强化学习状态及动作空间大小，搭建了配电网抢修恢复测试环境。在不同恢复模式、多个故障场景下的测试结果表明：强化学习在提出的多个评价指标下综合表现稳定，可以作为灾后动态抢修的可选方案。

The post-disaster emergency repair and reconfiguration plan of the faulty distribution system are confronted with the challenges from the uncertainty of the disaster, the deployment of multiple emergency repair teams and the coupling of emergency repair and reconfiguration. This paper builds a model for emergency repair deployment of multiple repair teams based on reinforcement learning. A state coarse screening mechanism is designed to fix the size of the state and action space of reinforcement learning. An environment based on OpenAI Gym is constructed for the repair and reconfiguration of the distribution system. The experimental results show that reinforcement learning has a stable comprehensive performance under the proposed multiple evaluation indicators, and it can be used as an optional solution for dynamic repair after a disaster.

近年来强化学习愈发体现其强大的学习能力，2017年AlphaGo在围棋上击败世界冠军，同时在复杂竞技游戏星际争霸2和DOTA2中人类的顶尖战队也败于AI之手，但其自身又存在着自身的弱点，在不断的发展中瓶颈逐渐出现。分层强化学习因为能够解决其维数灾难问题，使得其在环境更为复杂，动作空间更大的环境中表现出更加优异的处理能力，对其的研究在近几年不断升温。对强化学习的基本理论进行简要介绍，对Option、HAMs、MAXQ这3种经典分层强化学习算法进行介绍，之后对近几年在分层的思想下提出的分层强化学习算法从3个方面进行综述，并对其进行分析，讨论了分层强化学习的发展前景和挑战。

In recent years, reinforcement learning has increasingly reflected its strong learning ability. In 2017, AlphaGo beat the world champion in go. Meanwhile, in the complex competitive games StarCraft 2 and dota2, the top human teams are also defeated by AI. However, it has its own weaknesses, and the bottleneck gradually appears in the continuous development. Hierarchical reinforcement learning can solve the problem of dimension disaster, which makes it show more excellent processing ability in the environment with more complex environment and larger action space. This paper briefly introduces the basic theory of reinforcement learning. It introduces three classical hierarchical reinforcement learning algorithms, option, hams and MAXQ. It summarizes and analyzes the hierarchical reinforcement learning algorithm proposed in recent years under the idea of stratification from three aspects. It discusses the development prospects and challenges of hierarchical reinforcement learning.

为探究常规降雨作用下城市路网性能时变性,建立合理的路网韧性评价体系,首先,构建城市道路路段交通流量降雨损伤的长短期记忆网络(LSTM)模型;其次,定义具有时变特性的路网性能函数;然后,基于韧性理念推导出路网时变韧性计算模型;最后,基于某城市降雨信息与路网交通数据及Sioux Falls网络,分析降雨对路段与路网时变特性的作用效果。结果表明:当降雨持续时间或降雨量增加时,路段工作日交通流量损伤均有增加趋势;路网韧性是各相关路段协同作用的综合体现,因而其对降雨作用呈现出较交通流量损伤更为迟钝的响应,且其值在常规降雨条件下通常不小于0.9;少雨水季节明显强于多雨水季节的路网韧性,而路网年韧性在未受到降雨灾害影响时一般会维持在一个较高水平上,且其在相近年份之间的差异并不显然。

To explore the time-varying performance of urban road networks under regular rainfall and establish a reasonable evaluation system for road network resilience, an LSTM model for the rainfall-induced traffic flow degradation in urban road segments was first constructed, and a network performance function with time-varying characteristics was second defined. Then, based on the resilience concept, a time-varying resilience calculation model for road networks was derived. Finally, the effect of rainfall on the time-varying characteristics of road segments and networks was investigated based on rainfall information and traffic data of a certain city and the Sioux Falls network. The results show that when the duration or amount of rainfall increases, the traffic flow degradation of road segments increases on weekdays. The road network resilience is a comprehensive reflection of the synergistic effect of various related road segments, and therefore its response to rainfall is slower than that of traffic flow degradation, and its value is generally not less than 0.9 under regular rainfall conditions. The road network resilience during low rainfall seasons is significantly stronger than that during high rainfall seasons, and the annual resilience of road networks is usually maintained at a higher level when not affected by rainfall disasters, and the difference between adjacent years is not significant.