This paper presents the impact prediction model for new energy vehicles, primarily utilizing grey prediction and random forest. With the global emphasis on environmental protection, new energy vehicles have been developing rapidly due to their green and energy-saving and low-consumption characteristics. This paper initially reviews the related studies and highlights that coverage guidance and technological advancement are the primary driving forces for the enhancement of modern energy vehicles. Then the data sources and pre-processing process are introduced, and a number of key indicators reflecting market trends, policy support and technological progress are selected. Next, each feature’s impact on the advancement of cutting-edge energy vehicles is examined using a random forest model, and the results show that factors such as government subsidies and technological progress are the most important. Meanwhile, a gray prediction model is used to forecast the market share of new energy vehicles in the next decade, which is expected to continue to grow and exceed 50% after 2028. Finally, the paper emphasizes the advantages of new energy vehicles in reducing tailpipe emissions, but also points out that carbon emissions during battery production and use need to be considered comprehensively. It is concluded that policy support, technological advances and infrastructure development will drive the development of new energy vehicles, enabling them to gradually replace conventional vehicles as the mainstream in the next decade.
New Energy Vehicle Forecasting Based on Gray Forecasting and Random Forest
Sustain. Civil Infrastruct.
International Conference on Smart Applications and Sustainability in the Artificial Intelligence of Things ; 2024 ; Türkiye June 06, 2024 - June 08, 2024
2024-12-27
13 pages
Article/Chapter (Book)
Electronic Resource
English
New Energy Vehicle Development and Electricity Demand Forecasting Based on Random Forest Model
DOAJ | 2024
|Forecasting road traffic conditions using a context-based random forest algorithm
Taylor & Francis Verlag | 2019
|EV Flow Forecasting in Highway Using Random Forest Machine Learning Model
Springer Verlag | 2025
|