This paper presents a method for predicting power-grid failure rates in typhoons and water logs and suggests a strategy for improving network elasticity after the disaster. It is crucial for the operation and maintenance of power distribution systems during typhoon and. To address the decline in power supply capability of distribution networks during typhoons, it is necessary to fully utilize distributed resources in distribution networks and enhance the resilience of distribution networks during disasters from multiple aspects such as comprehensive power supply. To improve the accuracy of typhoon-induced hazard intensity forecasting, an LSTM network enhanced with multi-scale attention (LSTM-MSA) is developed, which overcomes the deficiency of the traditional LSTM model that cannot capture the local attention mechanism.
[PDF Version]