Abstract: To address the charging gap issue for electric vehicles in both urban and rural areas of Pukou, and to enhance the intelligence of charging services for an improved user experience, this paper proposes a method for predicting electric vehicle charging loads based on FCM clustering and BiLSTM. Firstly, to identify the internal structure and patterns of charging loads, FCM clustering is applied to the daily charging load dataset, dividing the data into different clusters, with each cluster representing samples with similar charging load characteristics. Subsequently, tailored BiLSTM models are constructed for training and prediction based on the distinct sample features within each cluster. Model parameters are adjusted to enhance prediction accuracy. Through comparative experiments, validating the effectiveness and practicality of the approach.