基于非参数核密度估计的集装箱码头交通需求预测模型

Traffic demand forecasting model for container terminal based on non-parametric kernel density estimation

针对现有集装箱集疏港时间概率分布建模中需要假设参数分布的问题,基于非参数核密度估计理论建立集装箱码头交通需求预测模型.非参数核密度估计的核函数选取高斯核,最优带宽由交叉验证法求得,通过检验、K-S检验和后验检验对比分析了核密度估计与两种传统参数模型的估计效果,并应用该模型预测DCT码头的交通需求.结果表明:非参数核密度估计模型具有更高的拟合精度、稳定性和适用性,得到的概率密度曲线能更加准确反映出口箱集港时间和进口箱疏港时间的整体分布形态,基于非参数核密度估计的集装箱码头交通需求预测模型具有比传统的参数模型更高的预测精度,可为集装箱码头基础设施规划、集疏港通道的道路交通管理、码头资源优化配置和调度等问题的研究提供更准确的交通量和作业任务量预测.

To address the inadequacies associated with present parametric density estimations for containers’ delivery and pick up time distributions, a traffic demand forecasting model based on non-parametric kernel density estimation was developed.Gaussian kernel was chosen as the kernel function and the optimal window width was obtained by the cross-validation method.The χ~2 test, K-S test and posteriori test were used to compare the goodness-of-fit of the proposed probabilistic model and two conventional parametric distribution models, and the proposed model was applied to forecast the traffic demand of DCT. The results demonstrate that the proposed non-parametric estimation has better accuracy, stability and applicability. The probability density curve obtained can more accurately reflect the overall distribution pattern of containers’ delivery and pick up time. The traffic demand forecasting model based on non-parametric kernel density estimation has higher prediction accuracy than that of the conventional parametric distribution models, which can provide more accurate traffic volume and task volume prediction for the infrastructure planning of container terminal, road traffic management, allocation and scheduling of terminal resources.