交通韧性是指在极端条件下交通系统能够通过自身抵抗、减缓以及吸收的方式维持其系统基本功能和结构的能力，或者能够在合理的时间和成本内恢复原始平衡或者新平衡状态的能力。受全球增温、海平面上升以及快速城市化的影响，极端事件的风险日益增加，从而导致城市交通运输基础设施运营面临着严峻的挑战。在此背景下，如何衡量极端事件下城市交通韧性强度(包括不同极端天气事件强度对其强度的影响)，如何监测其时空分布特征和演变趋势，以及多长时间交通运输系统能够恢复正常状态?针对这些问题，目前还缺乏有效的监测方法，尤其是缺乏气候变化对交通韧性影响的时空动态变化监测。因此，如何精准识别极端事件下城市交通韧性的状态，提升自然灾害交通防治水平亟待解决。而随着大数据挖掘技术和时空预测深度学习方法的发展，为重建城市交通韧性强度时空数据集，进而揭示历史极端事件影响下城市交通韧性强度时空演变特征、变化趋势以及影响机制提供了可能。论文对国内外近50年来交通韧性研究进行了梳理和概括，结合国内外交通韧性的相关研究成果对已有的研究中存在的不足进行了评述；并指出了气候变暖情况下交通韧性研究的重点领域和方向，旨在为今后开展交通韧性研究提供新的思路。

Urban transportation resilience reflects the ability of the transportation system to maintain its basic functions and structure through its resistance, mitigation, and absorption under extreme conditions, or the ability to restore the original equilibrium or reach a new equilibrium state within a reasonable time and with reasonable cost. Global warming, sea-level rise, and rapid urbanization all increase the risk of compound extreme weather events, presenting challenges for the operation of urban-related infrastructure including transportation infrastructure. In this context, some questions become important. For example, how to measure the strength of urban transportation resilience under extreme weather events (including the impact of different extreme weather event intensities on its strength); how to monitor its spatial and temporal features and evolution trends; and how long will it take for the entire system to restore balance? At present, effective monitoring methods for transportation resilience under the influence of extreme events are lacking, especially the monitoring of the temporal and spatial dynamic changes of transportation resilience under climate change, to answer these questions. Therefore, it is urgently needed to solve the problem of accurately identifying the state of urban transportation resilience under extreme weather events and improving the level of prevention and control of transportation system impact of natural hazard-related disasters. The development of big data mining technology and deep learning methods for spatiotemporal prediction made the construction of spatiotemporal datasets for evaluating and predicting urban transportation resilience possible. Such datasets can reveal the spatiotemporal evolution features, changing trends of urban transportation resilience intensity under the influence of extreme weather events, as well as the mechanism of influence. It indicates the key research areas that should be focused on for transportation resilience under climate warming. This article reviewed and summarized the research on transportation resilience in China and internationally in the past 50 years, analyzed the deficiencies in the existing research based on the relevant research results of transportation resilience in China and globally, and identified the key areas and directions of the research on transportation resilience under climate warming in order to provide new ideas for future research on transportation resilience.

In the context of large-scale grid connection of distributed energy, during the reconfiguration of the distribution network, the availability of distributed energy and the load of the distribution system may be inconsistent with the prediction due to the influence of environmental factors and human factors. If the distribution network reconfiguration is still carried out according to the expected offline optimization scheme, there may be reliability problems of voltage over-limits and economic problems of increased network loss in the actual reconfiguration process. Therefore, the reconfiguration plan formulated in advance can give some guidance to the dispatch operator, but it may not be directly used in the actual reconfiguration process. This paper proposes a deep reinforcement learning approach to solving the electric distribution network reconfiguration. Based on the uncertainty of distributed energy output and network load in the distribution network, the online algorithm of distribution network reconfiguration realizes the second-level solution of distribution network reconfiguration, through day-ahead training of the neural network.