Prediction of Power Grid Emergency Material Resources under Meteorological Disasters

Power Grid accidents caused by sudden natural meteorological disasters have the characteristics of suddenness, complexity and uncertainty. In order to improve the efficiency of power grid emergency repairs, a method for predicting emergency material resources under the conditions of power grid meteorological disasters combining case-based reasoning, deep belief network and deep learning is proposed. This method is based on meteorological data, power grid maintenance data and geographic environment data. At the same time, the method uses case-based reasoning to determine the appropriate input and output structure of the prediction model, and uses different methods to process and quantify according to the characteristics of disagreeing input factors. Use deep belief networks to complete case adaptation, and integrate accident scale information to establish a dynamic power grid emergency material resources prediction model. The analysis result shows that the emergency material resources prediction method proposed in this paper can analyze various characteristic factors comprehensively, and combine the scale of the accident to establish the relationship between the emergency material resources demand of the power grid, and accurately predict the material demand for the emergency response of the power grid under the weather disaster, and provide a scientific reference for emergency response of power grid.