基于最优组合预测模型的港口集装箱吞吐量预测

根据港口集装箱吞吐量非线性增长等特点,建立了三次指数平滑预测模型、灰色系统预测模型及BP神经网络预测模型等单项预测模型。鉴于单项预测模型的局限性,提出了以测试数据的预测误差绝对值加权和最小为最优化准则的最优组合预测模型,采用线性规划的方法确定最优组合的权系数。最后,给出一个实例进行应用和分析。

Forecasting Container Throughput of Port Based on Combined Forecasting Model

According to the non-linear increasing characteristics of the container throughput of port, triple exponential smoothing forecasting model, grey system forecasting model and BP artificial neural network forecasting model are established respectively, Due to the limitations of each single forecasting model, this paper put forward the combined forecasting model based on the optimum principle of the minimal sum of the forecasting error absolute values, the weighting coefficients are derived by linear programming. Finally, a practical case is given.