自适应遗传算法优化模糊变权重的复杂系统时间序列组合预测方法

来源期刊:中南大学学报(自然科学版)2013年第11期

论文作者:李冠南 单汨源

文章页码:4542 - 4548

关键词:复杂系统;预测模型;组合预测;模糊变权重

Key words:complex systems; forecasting model; combination forecasting; fuzzy variable weight

摘    要:针对复杂系统时间序列预测精度不高问题,将复杂系统时间序列组合预测模型的权系数视为模糊数,以模糊区间的大小作为模糊变权重复杂系统时间序列组合预测模型目标函数,利用自适应遗传算法优化复杂系统时间序列组合预测模型目标函数的权重系数,建立基于遗传算法优化模糊变权重的复杂系统时间序列组合预测方法。仿真结果表明:此模糊自适应变权重非线性组合预测模型的精度较高,并且平均误差和预测平方根误差均较小;所提出的基于遗传算法优化模糊变权重组合预测模型的最大相对误差为2.89%,小于各预测模型中最小的最大相对误差3.24%,且平均误差和平方根误差均较小。

Abstract: As for the low forecasting precision problem about time series in complex system, a time series combined forecasting model of complex systems was established based on the method of fuzzy variable weight optimized by adaptive genetic algorithm, meanwhile the model was handled by using of some measurements such as combined forecasting model of weight being regarded as fuzzy numbers, objective function of combined forecasting model on time series of complex systems due to fuzzy variable weight based on the fuzzy interval size and the weight of the combined forecasting model optimized by adaptive genetic algorithm. The simulation results show that the precision of nonlinear combined forecasting model is higher than that of every single combined forecasting model. The most relative error value of the combined forecasting model is 2.89%, which is less than the least value 3.24% of the most relative error of the single forecasting model, and the mean error and square root error of the combined forecasting model is less.

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号