Power load probability prediction method and system based on conditional variation auto-encoder

The invention discloses a power load probability prediction method and a power load probability prediction system based on a conditional variation auto-encoder, which relate to the technical field of power load prediction and take a load multi-step prediction result of a preset load prediction model as an input basis. A shape error, a time error and a root-mean-square error between a prediction sequence and an actual sequence are combined to jointly serve as a loss function to train a conditional variation auto-encoder, the improved loss function can mine the overall difference between power load sequences, and mutation and randomness of power load data can be sensed and captured in a self-adaptive mode. According to the method, the prediction precision is improved, and the technical problems that an existing power load prediction method only depends on MSE or MAE to measure the error between a prediction value and an actual value, the difference between a prediction sequence and an actual sequence is difficu