Relevance vector machine with optimal hybrid kernel function for electric vehicles ownership forecasting: The case of China

Abstract

Electric Vehicles (EVs) ownership forecasting is of great significance to deal with the opportunities and challenges brought by the rapid development of EVs. However, most of the existing EVs ownership forecasting methods are model-driven methods that based on artificial experience, leading to the low reliability of the forecasting results. An ideal choice is data-driven method that can automatically mine regression relationships from available data. In this paper, we propose a data-driven method based on Relevance Vector Machine (RVM), which is suitable for small sample cases such as EVs ownership forecasting and can automatically find the changing pattern of EVs ownership to make high precision forecasting results. In the proposed method, an optimal hybrid kernel function is proposed to further improve the forecasting effect of RVM. Besides, factors affecting EVs are analyzed comprehensively to determine the input variables of the proposed method. The simulation results based on the data from 2011 to 2019 show that the proposed method outperforms some existing mature methods and other data-driven methods. Then, the EVs ownership forecasting results of China up to 2030 are given based on the proposed method.

Keywords

• Electric vehicles ownership
• Forecasting
• Relevance vector machine
• Hybrid kernel function