A Dynamic Assessment and Early Warning Research for Inundation Risk of Electric Power Facilities

To solve the problem of power supply failure caused by rainstorm inundation, a dynamic assessment and early warning method for inundation risk of electric power facilities based on two-dimensional hydrodynamic model is proposed in this paper. The Chicago rainfall model and two-dimensional hydrodynamic model are used to model the rainstorm inundation of power facility nodes. The weighted comprehensive evaluation method is used to calculate the risk probability of the failure event of the flooded facilities. A short-term load prediction model combining variational mode decomposition (VMD) and long short-term memory (LSTM) is proposed to forecast the short-term load of the grid nodes during the rainstorm. A classification method of risk and warning levels is proposed to mark nodes, in order to provide scientific decision-making basis for the managers of electric power facilities. The effectiveness of the proposed method is verified by taking a regional power grid as an example. The application process of the proposed method is further illustrated by taking the power grid of a certain region as an example. The feasibility and effectiveness of the proposed method are proved.