基于潜在出行意图的民航旅客移动模型

Civil Aviation Passenger Mobility Model Based on the Potential Trip Purpose

人类出行具有规律性,对人类移动规律构建移动模型具有理论意义和现实需求。现有移动模型通常基于人类出行距离具有标度性这一假设,且未考虑出行次数和基础设施网络的影响。针对上述问题,利用民航旅客出行数据集进行统计分析发现旅客出行有以下特性:出行距离分布不具有标度性,出行次数具有各向异性,旅客扩散随出行次数不同具有不同的变化趋势。为了刻画民航旅客出行特性,提出了基于潜在出行意图的民航旅客移动模型(passenger mobility model based on potential trip purpose,PMMPTP)。首先,考虑旅客出行与目标城市经济因素有关,提出了旅客出行城市的选择概率计算方法。然后,考虑旅客出行具有探索和返回特性,给出了计算旅客探索新机场和返回历史机场的概率的方法。实验中,先利用PMMPTP模型模拟民航旅客的出行特性,再通过对机场吞吐量和航线吞吐量的预测检验其有效性。实验结果表明,该模型能较好地拟合真实数据,有效解决了大量低频出行旅客的出行建模。

Human mobility has regularity.It has theoretical significance and realistic needs to build mobility models of human move- ment.Previous models were usually based on the assumption that human mobility is scalable and did not take into account the times of trips and influence of infrastructure network.To address these problems,by analyzing passengers＇ traveling data sets of civil aviation,the following characteristics of passengers＇ traveling were found：the trip distances of passengers are not scale-free,the trip number of times is anisotropic,and passengers＇ movements have different trends along with different numbers of trip times.ln order to describe the characteristics of passengers＇ travelling data,a passenger mobility model based on potential trip purpose （PMMPTP） was proposed.Firstly,the model considered that passengers＇ travel has relationship with the economic factors of destination cities,and a method for calculating the selection probability of a city was proposed.Secondly,the exploration and return mechanism of passengers＇ travelling was taken into account.Then,a method for calculating the probability that passengers explore new airports and return to the historic airports was proposed.The simulation experiments firstly simulated the travel characteristics of civil aviation using PMMPTP model and then tested the validity of the model by predicting the throughput of airport and airline.The results showed that the model can fit the actual data of civil aviation travel,and effectively solve the problem of modeling low frequency passenger＇s trips.