主管:中国科学院
主办:中国优选法统筹法与经济数学研究会
   中国科学院科技战略咨询研究院

中国管理科学 ›› 2024, Vol. 32 ›› Issue (1): 106-114.doi: 10.16381/j.cnki.issn1003-207x.2021.2567

• • 上一篇    

基于离散时间灰色幂模型的新能源汽车销售量预测

刘连义1,刘思峰1,2(),吴利丰3   

  1. 1.南京航空航天大学经济与管理学院, 江苏 南京 211106
    2.西北工业大学管理学院, 陕西 西安 710072
    3.河北工程大学管理工程与商学院, 河北 邯郸 056107
  • 收稿日期:2021-12-09 修回日期:2022-01-21 出版日期:2024-01-25 发布日期:2024-02-08
  • 通讯作者: 刘思峰 E-mail:sfliu@nuaa.edu.cn
  • 基金资助:
    国家自然科学基金项目(72271124);江苏省自然科学基金青年项目(BK20230870);江苏省社会科学基金青年项目(23GLC001);中央高校基本科研业务费(NS2023043);中国博士后科学基金面上项目(2022M721596);国家自然科学基金与英国皇家学会国际合作交流项目(71811530338);科技部科技创新引智基地项目(G20190010178);科技部外国专家高端引智项目(G2021181014L);中国博士后科学基金特别资助项目(2019TQ0150)

New Energy Vehicle Sales Forecast Based on Siscrete Time Grey Power Model

Lianyi Liu1,Sifeng Liu1,2(),Lifeng Wu3   

  1. 1.School of Economics and Management, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
    2.School of Management, Northwestern Polytechnical University, Xi’an 710072, China
    3.School of Management Engineering and Business, Hebei University of Engineering, Handan 056107, China
  • Received:2021-12-09 Revised:2022-01-21 Online:2024-01-25 Published:2024-02-08
  • Contact: Sifeng Liu E-mail:sfliu@nuaa.edu.cn

摘要:

准确预测新能源汽车市场的发展趋势,对于行业的发展规划和中国能源战略目标的实现具有重要现实意义。为此,本文在现有两类灰色幂模型的基础上,利用累加数据的幂指数数据进行直接建模,提出了一种含多参数的改进灰色幂模型,从而可以反映系统历史值与时序因素对系统当前值的非线性作用。此外,根据灰导数的信息覆盖原理,给出模型的差分形式和派生离散形式,记为DTGPM,并给出了模型的时间响应式函数,避免了传统灰色幂模型复杂的积分求解过程。进一步,利用启发式算法对DTGPM模型的幂参数进行优化,并通过仿真试验和实例验证分析了模型的预测有效性。最后,对新能源汽车的市场销售量进行预测,预测结果显示,中国的新能源汽车销售量会在2022年达到473万辆,并预计在2025年超过千万辆,销售量占汽车新车总销量的23.5%。

关键词: 灰色幂模型, 预测算法, 新能源汽车, 销量预测

Abstract:

Accurate prediction of the new energy vehicle market’s development trend is of great practical significance for the realization of the development planning of the industry and China's energy strategic goals. Therefore, based on the existing two types of grey power models, an improved grey power model with multiple parameters is proposed, which can reflect the nonlinear effect of historical value and time sequence factors on the current value of the system. In addition, according to the information coverage principle of grey derivative, the differential form and derived discrete form of the model are given, denoted as DTGPM, and the time response function of the model is given, which avoids the complex integral solution process of the traditional grey power model. Furthermore, the heuristic algorithm is used to optimize the power parameters of the DTGPM model, and the prediction effectiveness of the model is verified by simulation experiments and practical example. Finally, the market sales volume of new energy vehicles is forecast. The forecast results show that the sales volume of new energy vehicles in China will reach 4.73 million in 2022, and is expected to reach nearly 10 million in 2025, accounting for 23.5% of the total sales volume of new vehicles.

Key words: grey power model, prediction algorithm, new energy vehicles, sales forecasts

中图分类号: