A network‐based dynamic air traffic flow model for short‐term en route traffic prediction

Abstract

This paper presents a dynamic network-based approach for short-term air traffic flow prediction in en route airspace. A dynamic network characterizing both the topological structure of airspace and the dynamics of air traffic flow is developed, based on which the continuity equation in fluid mechanics is adopted to describe the continuous behaviour of the en route traffic. Building on the network-based continuity equation, the space division concept in cell transmission model is introduced to discretize the proposed model both in space and time. The model parameters are sequentially updated based on the statistical properties of the recent radar data and the new predicting results. The proposed method is applied to a real data set from Shanghai Area Control Center for the short-term air traffic flow prediction both at flight path and en route sector level. The analysis of the case study shows that the developed method can characterize well the dynamics of the en route traffic flow, thereby providing satisfactory prediction results with appropriate uncertainty limits. The mean relative prediction errors are less than 0.10 and 0.14, and the absolute errors fall in the range of 0 to 1 and 0 to 3 in more than 95% time intervals respectively, for the flight path and en route sector level. airport conditions, airline operation and human factors. [4]. Furthermore, the dimension of the model depends on the number of aircraft under consideration, which demands a huge computational cost in real context to resolve. Thus, in practice, it is difficult to make sound online air traffic control strategies based on the trajectory-based model due to the short forecast horizon and the expensive computational cost.Efficient ATFM requires reasonable prediction of the whole traffic flow situations in the specified airspace, rather than the temporal-spatial information of individual aircraft. Therefore, the aggregate air traffic flow models are introduced recently, which focus on the overall distribution of the air traffic flow in the airspace volumes of interest [5][6][7][8][9][10][11][12][13][18][19][20][21][22][23][24]. Because the aircrafts in the airspace volumes are spatially aggregated, the dimension of the aggregated model depends solely on the number of airspace volumes rather than the total number of aircrafts in the airspace, which will reduce the computational cost significantly. In addition, because the behaviour of the individual aircraft is not taken into account in the aggregated model, it is less sensitive to the uncertainty factors related to individual aircraft, such as the departure delay and the weather, and thus, a longer forecast time horizon with less prediction errors can be achieved.Recently, the aggregated approach is widely discussed in the literatures [5][6][7][8][9][10][11][12][13][18][19][20][21][22][23][24]. A stochastic framework with linear dynamic system model was developed by Sridhar et al., where the dimension of the model depends on the number of control volumes by introducing split parameters to d...

Air Traffic Flow Prediction with Spatiotemporal Knowledge Distillation Network

“…Air trafc fow management (ATFM), recognized as a widely implemented and efective strategy, plays a pivotal role in ensuring efcient and safe air transportation operations [4]. Air trafc fow prediction, as the key part of the ATFM system, helps the controllers to formulate control strategies in advance, thereby alleviating air trafc congestion [5,6].…”

A Deep Learning Approach for Short-Term Airport Traffic Flow Prediction

“…The flow model-driven algorithms generally learn the evolution pattern of the traffic flow by some handcrafted traffic models. Prior knowledge is required to design the traffic model to forecast future traffic flow, including the cell transmission model [7], the queuing theory model [8], and the aggregate flow model [9][10][11], and so forth. However, the traffic state is influenced by many factors so that it may be difficult to fully illustrate unsteady air traffic flow by a specific model.…”

Data-driven network modeling for airspace optimization through airway re-structurization and traffic flow prediction

“…Accurate tactical air traffic flow prediction is essential in advising air traffic controllers about the forthcoming traffic flow, which can support the decision-making and evaluation of control strategies of tactical ATFM [59]. When the traffic demand is foreseen to exceed the capacity of a particular airspace, the responsible ATFM unit can inform the flights planned to fly in the affected area as soon as practicable of the delays expected or the restrictions that will be applied.…”

“…In the presence of the increasing traffic flow and limited capacity, an accurate shortterm air traffic flow prediction, i.e., 0-2 hour look-ahead time [82], in the airspace can be vital for ATCOs managing the forthcoming traffic flow situation and evaluating control strategies [59]. In this way, tactical ATFM measures can be planned and executed in advance in a more efficient manner to maximize the use of the existing airspace capacity.…”

“…In this chapter, to identify the transition phases in airspace capacity, a data-driven Besides identifying the airspace capacity overload, in the presence of limited capacity, an accurate short-term air traffic flow prediction, i.e., 0-2 hour look ahead time [82], can be vital for ATCOs managing the forthcoming traffic flow situation and evaluating control strategies [59]. For instance, ATCOs can execute the agreed tactical measures, such as traffic re-routing and flight level allocation, in advance, to provide a smooth and efficient flow of traffic where demand is foreseen to exceed capacity or disruptions such as convective weather appears, to utilize the available capacity to the maximum extent [60].…”