Grey correlation-based integrated learning prediction method and system for electric vehicle battery replacement demand

Abstract

The invention discloses a grey correlation-based integrated learning prediction method and system for an electric vehicle battery replacement demand. The method comprises the steps: constructing a data set, carrying out the preprocessing, and dividing the preprocessed data set into a training set and a test set; selecting k base learners, and enabling each base learner to train and predict the samples of the training set in a cross validation mode; for each input sample in the test set, selecting an optimal similar day training set through grey correlation analysis; establishing a prediction deviation minimization optimization model according to the prediction result of each base learner in the optimal similar day training set, and adopting an L1 norm with a weight coefficient as a regularterm; and solving the weight coefficient of each base learner based on the optimization model to obtain an integrated predictor, and obtaining an integrated learning prediction result based on the integrated predictor. The method can effectively reduce the prediction deviation, has a better prediction effect on data with large random fluctuation, and can better adapt to a data set obtained in practice.

Description

technical field [0001] The present invention relates to the technical field of machine learning, in particular to an integrated learning prediction method and system based on gray relational electric vehicle battery replacement requirements. Background technique [0002] Cars are people's daily way of travel, but traditional fuel vehicles will bring serious environmental pollution problems, such as the pollution of large steam and water resources, and global warming. The emergence of electric vehicles can reduce the use of traditional fossil energy, thereby reducing the emission of pollutants and playing a certain role in protecting the environment. The battery swap mode of electric vehicles can reduce charging time and improve user convenience. For example, in 2017, Beijing Automotive Industry Holding Co., Ltd. (BAIC) announced the implementation of the "Optimus Prime Project", which aims to promote the integrated development of new energy and electric vehicles through the...

AI Technical Summary

Problems solved by technology

Due to the fact that the distribution of data sets obtained in practice is not uniform, and such as the demand for battery replacement of electric vehicles, its volatility is greater and there is a strong uncertainty

Images