A line loss electric quantity prediction method based on a neural network-time sequence is provided. The line loss electric quantity is predicted according to the relation between power supply quantity and power consumption quantity, and the line loss electric quantity is P1 = PSu-PSa, wherein P1 is line loss electric quantity, PSu is power supply quantity, and PSa is power consumption. The step of calculating the power consumption comprises the steps of 1, establishing a source database, and collecting and storing historical data of historical power consumption of a user; 2, constructing a BPneural network-time sequence power consumption prediction model, and initializing parameters of the BP neural network; 3, inputing historical power consumption data and influence factor data of a user to train the BP neural network-time sequence power consumption prediction model, and obtaining a trained BP neural network-time sequence power consumption prediction model; and 4, predicting the power consumption through the trained BP neural network-time sequence power consumption prediction model. Therefore, the utilization rate of the power source data is improved and the accuracy of power consumption prediction is ensured, so that the integrity and quality of line loss prediction are improved.