THE FUTURE DEVELOPMENT OF NEW ENERGY VEHICLES BASED ON ARIMA TIME SERIES PREDICTION MODEL
Keywords:
New-energy electric vehicles, Multiple linear regression model, Pearson correlation analysis, ARIMA time series analysisAbstract
This paper mainly adopts the evaluation model based on gray correlation method, multiple linear regression model, the secondary polynomial regression model, studied the influence of various factors of new energy vehicles in China and the influence of traditional fuel vehicles, and then choose the prediction of the next ten years, collect new energy vehicles in the past seven years, using the Pearson correlation coefficient test the development of new energy electric vehicles and predictor, found that the strong correlation, and derived the corresponding index of the correlation coefficient. And the ARIMA time series model is used to predict the trend of new energy electric vehicles in the next decade. Research shows that the research and development of new energy electric vehicles is very important for environmental protection. This paper calls on people to buy and ride in new energy electric vehicles to reduce greenhouse gas emissions and promote green development.References
[1] Zhang Q, Du M A, Lin B. Driving total factor productivity: The spillover effect of digitalization in the new energy supply chain. Research in International Business and Finance, 2025, 75, 102764-102764.
[2] Fan B, Wen Z, Qin Q. Competition and cooperation mechanism of new energy vehicle policies in China’s key regions. Humanities and Social Sciences Communications, 2024, 11(1): 1640-1640.
[3] Liu B, Song C, Wang Q, et al. Research on regional differences of China’s new energy vehicles promotion policies: A perspective of sales volume forecasting. Energy, 2022, 248: 123541.
[4] Liu Q, Wen X, Cao Q. Multi-objective development path evolution of new energy vehicle policy driven by big data: From the perspective of economic-ecological-social. Appl Energy, 2023, 341: 121065.
[5] Huang Xiaoqing, Zhang Dongliang, Zhang XiaoSong. Energy management of intelligent building based on deep reinforced learning. Alexandria Engineering Journal, 2021, 60(1): 1509-1517.
[6] Zeng B, Yin F, Wang J, et al. Prediction and rationality analysis of new energy vehicle sales in China with a novel intelligent buffer operator. Engineering Applications of Artificial Intelligence, 2025, 143, 110030-110030.
[7] Wang Z, Niu S, Hu S, et al. How to promote sustainable consumption and development of NEV? Decoding complex interrelationships in consumer requirements and design practice. Journal of Cleaner Production, 2025, 486, 144524-144524.
[8] Jiang Jiachen, Mei Yuxin, Pan Yaoyao, et al. Development evaluation and sales forecast of new energy vehicles. Journal of Taizhou University, 2024, 46(03): 9-15.