基于粒子群算法的汽车保有量预测方法
Car Ownership Prediction Based on PSO
摘要 汽车保有量关系到城市建设与规划;针对汽车保有量预测问题,提出一种基于粒子群算法的汽车保有量预测方法,建立了一种多因素汽车保有量预测模型;选取城镇人口、居民消费水平、人均地区生产总值、道路网密度、公共交通车辆运营数、公共交通客运总量、油价7个指标作为汽车保有量的主要影响因素;利用主成分分析方法确定影响因素主成分,以主成分作为自变量,汽车保有量作为因变量,建立回归分析模型;运用粒子群算法,结合主成分回归预测值对汽车保有量进行预测;以2005~2014年上海市汽车保有量数据为依据,预测出上海市2020年汽车保有量约为400万辆,并对预测结果进行了分析.
Abstract:
Car ownership is related to the city's construction and the schematization.Aiming at the issue of the car ownership prediction,we bring forward a method,based on the Particle Swarm Optimization (PSO),to establish a multi-factor car ownership prediction model.The seven factors,including urban population,consumption level,gross regional domestic production,road network density,public transportation capacity,oil price,were chosen as the main factors to influence the car ownership.The principal components of the influence factors are ascertained by Principal Component Analysis (PCA).Using principal components as independent variable and car ownership as dependent variable can we build up the regression model.The car ownership prediction was calculated by the Particle Swarm Optimization (PSO),combining with regress predicted value of the principal components.Based on the statistics of car ownership in Shanghai from 1994 to 2005,the model arrive at the prediction that there will be 4 million cars in Shanghai in 2020,and an analysis is made due to the prediction.
Author: Luo Zhijun Huang Lixin Lei Ting Zheng Tingxuan Sun Yan
作者单位: 上海工程技术大学汽车工程学院,上海,201620 上海工程技术大学工程实训中心,上海,201620 上海工程技术大学中韩多媒体设计学院,上海,201620
刊 名 计算机测量与控制 ISTICPKU
年,卷(期): 2017, 25(9)
分类号: TP301.6
在线出版日期: 2017年11月13日
基金项目: 上海市大学生创新训练计划市级项目