摘要
GM(1,1)模型是应用范围极广的灰指数模型,其精度取决于背景值的构造形式和初始条件的选取。在误差最小化准则下构建了基于粒子群算法的GM(1,1)模型,同时对模型的背景值系数和初始值进行了优化。运用优化的模型分别对齐次指数序列、2017—2021年我国新能源汽车保有量进行拟合。实例分析表明,基于粒子群算法优化的GM(1,1)模型适合中长期预测并且具有更高的拟合精度。
GM(1,1)model is a gray index model with a wide range of applications,and its accuracy depends on the structure of the background value and the selection of initial conditions.The article proposes a GM(1,1)model based on the particle swarm algorithm to optimize the background value coefficients and initial conditions under the error minimization criterion.The optimized model is used to fit the sub-index sequence,the number of new energy cars of China from 2017 to 2021,and the wind power generation of China from 2012 to 2020.The example analysis shows that the new optimized GM(1,1)model is suitable for medium and long-term prediction and also has higher accuracy.
作者
王鲁欣
WANG Luxin(Basic teaching department,Jiangsu Shipping College,Nantong Jiangsu 226010)
出处
《中国科技纵横》
2023年第13期94-98,共5页
China Science & Technology Overview
基金
江苏省高职院校教师专业带头人高端研修项目资助
江苏高校“青蓝工程”资助。
关键词
GM(1
1)模型
粒子群算法
背景值
初始条件
误差最小化
GM(1,1)model
particle swarm optimization
background value
initial condition
error minimization
