基于优化GM(1,1)模型的港口吞吐量预测

Optimized GM(1,1) Model for Predicting Port Throughput

为有效预测具有振荡性质的港口吞吐量,提出基于正弦和具有自适应背景值的GM(1,1)优化模型。通过原始序列建立具有自适应背景值的GM(1,1)模型以描述总体趋势,利用正弦和描述残差中包含的周期性振荡规律,建立优化的GM(1,1)模型。利用该模型对广州港港口吞吐量数据进行模拟与预测,结果表明:基于优化的GM(1,1)模型,能够较好地描述具有周期振荡特征的港口吞吐量时间序列数据,模拟和预测精度都显著优于传统GM(1,1)模型,可将该模型用于具有振荡性质的吞吐量预测。

The optimized GM(1,1)model based on sum of sine and adaptive background value is built and used for effectively predicting the throughput with oscillatory characteristics.The GM(1,1)model with adaptive background values is built based on the original sequence to describe the overall trend,and then the GM(1,1)model is optimized using the sum of sine to describe the periodic oscillation rules of the residual.The model is used to simulate and predict the port throughput of Guangzhou port.The results show that the optimized GM(1,1)model can better reflect the time series data with periodic oscillation than the traditional GM(1,1)model and can give more accurate estimates.The optimized model is good for throughput prediction with oscillation.