Dynamic Evaluation of Distribution Network Reliability Based on Improved DNN with Large-scale Distributed Generations Access

With the access of large-scale distributed generations, its uncertainty brings great risk to the reliable operation of distribution network. Therefore, it is of great significance to consider the dynamic reliability evaluation of distribution network with large-scale distributed generations access. However, the traditional reliability evaluation method of distribution network is not suitable for evaluating the reliability index of distribution network with large-scale distributed generations access, which often leads to the difficulty of modeling and the sharp increase of calculation. Therefore, this paper proposes a large-scale distributed power generations access dynamic evaluation method based on improved depth neural network (IDNN), and uses Whale Optimization Algorithm (WOA) to optimize the relevant parameters of DNN. In addition, this paper uses the grey correlation analysis to preprocess the input variables of the depth neural network, and then selects the factors that have great influence on the reliability of the distribution network as its input variables, so as to improve the calculation speed of the model as much as possible under the premise of ensuring the accuracy. Finally, an urban distribution network is selected for analysis and evaluation to verify the effectiveness of the proposed method.