Short-term traffic flow forecasting is a significant part of intelligent transportation system.In some traffic control scenarios,obtaining future traffic flow in advance is conducive to highway management department t...Short-term traffic flow forecasting is a significant part of intelligent transportation system.In some traffic control scenarios,obtaining future traffic flow in advance is conducive to highway management department to have sufficient time to formulate corresponding traffic flow control measures.In hence,it is meaningful to establish an accurate short-term traffic flow method and provide reference for peak traffic flow warning.This paper proposed a new hybrid model for traffic flow forecasting,which is composed of the variational mode decomposition(VMD)method,the group method of data handling(GMDH)neural network,bi-directional long and short term memory(BILSTM)network and ELMAN network,and is optimized by the imperialist competitive algorithm(ICA)method.To illustrate the performance of the proposed model,there are several comparative experiments between the proposed model and other models.The experiment results show that 1)BILSTM network,GMDH network and ELMAN network have better predictive performance than other single models;2)VMD can significantly improve the predictive performance of the ICA-GMDH-BILSTM-ELMAN model.The effect of VMD method is better than that of EEMD method and FEEMD method.To conclude,the proposed model which is made up of the VMD method,the ICA method,the BILSTM network,the GMDH network and the ELMAN network has excellent predictive ability for traffic flow series.展开更多
Road traffic flow forecasting provides critical information for the operational management of road mobility challenges, and models are used to generate the forecast. This paper uses a random process to present a novel...Road traffic flow forecasting provides critical information for the operational management of road mobility challenges, and models are used to generate the forecast. This paper uses a random process to present a novel traffic modelling framework for aggregate traffic on urban roads. The main idea is that road traffic flow is random, even for the recurrent flow, such as rush hour traffic, which is predisposed to congestion. Therefore, the structure of the aggregate traffic flow model for urban roads should correlate well with the essential variables of the observed random dynamics of the traffic flow phenomena. The novelty of this paper is the developed framework, based on the Poisson process, the kinematics of urban road traffic flow, and the intermediate modelling approach, which were combined to formulate the model. Empirical data from an urban road in Ghana was used to explore the model’s fidelity. The results show that the distribution from the model correlates well with that of the empirical traffic, providing a strong validation of the new framework and instilling confidence in its potential for significantly improved forecasts and, hence, a more hopeful outlook for real-world traffic management.展开更多
为实现准确的机场流量短期预测,本文建立了基于二次分解方法的分解集成预测模型。首先,应用局部加权回归周期趋势分解(STL,seasonal and trend decomposition procedure based on Loess)算法将原始时间序列分解为趋势项、季节项和余项3...为实现准确的机场流量短期预测,本文建立了基于二次分解方法的分解集成预测模型。首先,应用局部加权回归周期趋势分解(STL,seasonal and trend decomposition procedure based on Loess)算法将原始时间序列分解为趋势项、季节项和余项3个分量,并计算其样本熵。其次,应用遗传算法(GA,genetic algorithm)优化变分模态分解(VMD,variational mode decomposition)参数,对熵值较大的分量进行二次分解。再次,使用极端梯度提升(XGBoost,extreme gradient boosting)对二次分解后的所有分量进行预测,采用加和集成得到最终的预测值。最后,采集国内典型机场实际运行数据进行实例分析。针对北京首都国际机场60 min进场、离场流量时序,本文模型预测的均等系数(EC,equal coefficient)值分别为0.9703、0.9959,相比其他常用模型均有所提高。此外,对于上海浦东、上海虹桥、广州白云3个大型国际机场,本文模型在60 min、30 min统计尺度下进场和离场流量预测的EC值均在0.9700以上,15 min统计尺度下预测的EC值均在0.9500以上。结果表明,本文建立的二次分解集成预测模型具有良好的准确性和普适性,用于机场流量短期预测是可行和有效的。展开更多
基金Project(61873283)supported by the National Natural Science Foundation of ChinaProject(KQ1707017)supported by the Changsha Science&Technology Project,ChinaProject(2019CX005)supported by the Innovation Driven Project of the Central South University,China。
文摘Short-term traffic flow forecasting is a significant part of intelligent transportation system.In some traffic control scenarios,obtaining future traffic flow in advance is conducive to highway management department to have sufficient time to formulate corresponding traffic flow control measures.In hence,it is meaningful to establish an accurate short-term traffic flow method and provide reference for peak traffic flow warning.This paper proposed a new hybrid model for traffic flow forecasting,which is composed of the variational mode decomposition(VMD)method,the group method of data handling(GMDH)neural network,bi-directional long and short term memory(BILSTM)network and ELMAN network,and is optimized by the imperialist competitive algorithm(ICA)method.To illustrate the performance of the proposed model,there are several comparative experiments between the proposed model and other models.The experiment results show that 1)BILSTM network,GMDH network and ELMAN network have better predictive performance than other single models;2)VMD can significantly improve the predictive performance of the ICA-GMDH-BILSTM-ELMAN model.The effect of VMD method is better than that of EEMD method and FEEMD method.To conclude,the proposed model which is made up of the VMD method,the ICA method,the BILSTM network,the GMDH network and the ELMAN network has excellent predictive ability for traffic flow series.
文摘Road traffic flow forecasting provides critical information for the operational management of road mobility challenges, and models are used to generate the forecast. This paper uses a random process to present a novel traffic modelling framework for aggregate traffic on urban roads. The main idea is that road traffic flow is random, even for the recurrent flow, such as rush hour traffic, which is predisposed to congestion. Therefore, the structure of the aggregate traffic flow model for urban roads should correlate well with the essential variables of the observed random dynamics of the traffic flow phenomena. The novelty of this paper is the developed framework, based on the Poisson process, the kinematics of urban road traffic flow, and the intermediate modelling approach, which were combined to formulate the model. Empirical data from an urban road in Ghana was used to explore the model’s fidelity. The results show that the distribution from the model correlates well with that of the empirical traffic, providing a strong validation of the new framework and instilling confidence in its potential for significantly improved forecasts and, hence, a more hopeful outlook for real-world traffic management.
