Integrated learning method and system for predicting time-phased battery replacement demand interval of electric vehicle

Abstract

The invention discloses an integrated learning method and system for predicting a time-phased battery replacement demand interval of an electric vehicle. The method comprises the following steps: dividing a preprocessed data set into a training set and a test set; selecting k base learners, and training and predicting samples of the training set by each base learner in a cross validation mode; for each input sample in the test set, selecting an optimal similar day training set of the input sample through grey correlation analysis; according to a prediction result of each base learner in the optimal similar day training set, establishing an optimization model which meets a certain coverage rate and has a minimum interval width, and adopting an L1 norm with a weight coefficient as a regular term; and solving the weight coefficient required by an integrated predictor based on the optimization model to obtain the integrated predictor, and obtaining an integrated learning prediction result based on the integrated predictor. According to the method, the prediction interval width can be effectively reduced on the basis of meeting a certain coverage rate, and the solving speed is high.

Description

technical field [0001] The invention relates to the technical field of electric vehicles, in particular to an integrated learning method and system for forecasting intervals of intervals of electric vehicle battery swapping needs. Background technique [0002] Vigorously developing new energy vehicles is of great significance to promote energy conservation and emission reduction in my country's transportation sector, promote technological change in the automobile industry, and enhance the core competitiveness of my country's automobile manufacturing industry in the world. The new energy electric vehicle battery replacement mode has the advantages of low car purchase cost, efficient energy replenishment, and extended battery life. It effectively alleviates the anxiety about the range of new energy electric vehicles and brings new opportunities for technological innovation and development of the new energy industry. Although the number of electric vehicles in my country has 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