A risk analysis and prediction model of electric power GIS based on deep learning

Abstract

In the distribution and supply system of electric power, the regional-based grids and users are diverse and complicated, which leads to the association between operation of the power systems and its geographic information much more closely. Geographic information systems (GIS) have been becoming an indispensable part of the power information management system (PIMS). By combining the aid from equipment dynamic analysing in GIS and with the deep learning of nonlinear network structure, the complex functional models are able to simulate the situation of power grid equipment more efficiently. Based on this model, we are able to predict the risk of entire power grid and provide decision support for the grids management. We have collected multiple sets of historical grid-runtime data that come from provincial power grid systems as the input of the model, and combined with the prior standard training data to improve the accuracy of the risk prediction model, the methods demonstrate that the model has a highly prediction accuracy and full capability of achieving better results contrasted with other modern optimisation algorithms.