Electric energy metering method and system based on big data self-diagnosis

The invention relates to the technical field of electric energy metering, and discloses an electric energy metering method and system based on big data self-diagnosis, and the method comprises the following steps: 1, data collection and storage: collecting and storing a large amount of electric energy metering data; according to the electric energy metering method and system based on big data self-diagnosis, an LSTM model used for multivariable time series prediction is established through big data deep learning Tensorflow and a Keras deep learning library, and future values are predicted based on past values and predicted values of the past values instead of using discrete irrelevant features such as seasons. The model can be more stable by using a predicted value of a past value, meanwhile, after the model is fitted, a whole test data set can be predicted by using a Walk-Forward Split method and a Side-by-Side Split method, prediction and the test data set are combined, the scale of the test data set is adj