Optimization method and device of multi-feedforward prediction model, equipment and storage medium

The invention discloses an optimization method and device of a multi-feedforward prediction model, equipment and a storage medium. When the method provided by the embodiment of the invention is executed, the test data set of the target power equipment can be firstly obtained, and the prediction data set of the target power equipment is obtained based on the test data set through the pre-constructed preliminary multi-feedforward prediction model. And calculating a prediction error between the prediction data set and the operation index label of the test sample, and calculating a loss function value between the prediction data set and the operation index label of the test sample by using a time-varying loss function, thereby optimizing the preliminary multi-feedforward prediction model based on the loss function value and the prediction error. According to the method, the model is allowed to adjust the learning key point according to the dynamic change of the time sequence data in the optimization process throu