Risk Identification Method for Charging Load in Low-voltage Distribution Networks Based on Situational Awareness

With the growth of electricity demand and the development of a new power system dominated by renewable energy, the operational risk assessment of charging loads is crucial for the safe operation of the distribution network. This paper studies a risk identification method for charging loads based on situational awareness. First, a risk assessment index system for charging loads is constructed, and the corresponding weights of each index are calculated using the analytic hierarchy process to determine the impact of different indices on operational risk; then, based on the situational awareness model framework, deep learning methods are used to predict future state data of charging loads, constructing a risk identification model for charging loads based on fuzzy comprehensive evaluation; case simulation analysis is conducted, selecting the prediction results of the LSTM model as the predicted values of future state data, resulting in a prediction error rate of less than 3.46%. Using the predicted values as input, after fuzzy comprehensive calculation, the final predicted risk situation of charging loads is consistent with the actual situation, verifying the feasibility of this method.