Fault prediction of electric vehicle charging stations based on cooperative game strategy and DBO-BiLSTM

Aiming at the problem of high failure rate of electric vehicle charging pile, an electric vehicle charging pile failure prediction method based on cooperative game strategy and dung beetle optimisation algorithm-bidirectional long and short-term memory network (DBO-BiLSTM) is proposed. Firstly, the outliers are handled by parameter statistical distribution, the missing values are handled by mean padding, and the normalisation operation is performed on the processed data; secondly, multiple single-assignment methods are selected to calculate the feature weights, the combined weights are calculated by the cooperative game strategy, and the parameter feature matrix is enlarged; and then, the DBO-BiLSTM model is constructed, and under the simulation experiments, the accuracy rate of the training set and test set, the F1 coefficients are 0.89, 0.89, 0.90 and 0.89, respectively.Finally, relevant comparison experiments are constructed, and the results show that the proposed model has better performance, which verifies the effectiveness and reasonableness of the proposed model.