An integrated learning method and system for interval forecasting of battery replacement demand for electric vehicles in different time periods

Abstract

The invention discloses an integrated learning method and system for predicting intervals of electric vehicles' battery replacement needs in time intervals, including: dividing a preprocessed data set into a training set and a test set; selecting k base learners, and adopting a cross-validation method Let each base learner train and predict the samples of the training set; for each input sample in the test set, select the best similarity day training set of the input sample through gray relational analysis; according to the best similarity of each base learner Based on the prediction results in the daily training set, an optimization model that satisfies a certain coverage rate and minimizes the interval width is established, and the L1 norm with weight coefficients is used as the regular term; the weight coefficient required for the integrated predictor obtained based on the optimization model solution, An integrated predictor is obtained, and an integrated learning prediction result is obtained based on the integrated predictor. The invention can effectively reduce the width of the prediction interval on the basis of satisfying a certain coverage rate, and has a faster solution speed.

Description

technical field [0001] The invention relates to the technical field of electric vehicles, in particular to an integrated learning method and system for predicting the demand interval for electric vehicle swapping in different time periods. Background technique [0002] Vigorously developing new energy vehicles is of great significance to promoting energy conservation and emission reduction in my country's transportation sector, advancing technological changes in the automobile industry, and enhancing the core competitiveness of my country's automobile manufacturing industry in the world. The new energy electric vehicle battery swap mode has the advantages of low purchase cost, efficient energy replenishment, and extended battery life, which effectively alleviates the anxiety of the new energy electric vehicle's cruising range, and brings new opportunities for the technological innovation and development of the new energy industry. Although the number of electric vehicles in ...

AI Technical Summary

Problems solved by technology

These methods are all based on statistical learning methods for prediction, and the single machine learning method they rely on has its own work bias

Images