航空交通系统中，构建统一不同决策阶段的供需态势建模框架，对于实现多层级、多阶段的高效协同决策至关重要。为此，开展了基于异构Agent的航空交通网络供需态势统一建模研究。首先，表征了网络节点完备性与预测误差的函数关系，从理论上证明空域网络结构完备性对延误表征精度具有决定性影响；随后，将Agent交互机制与流体排队理论结合，构建了覆盖航班、机场与空域的多元要素耦合动态框架。通过定义航班、机场、扇区三类异构Agent，建立状态迁移与拥堵/延误传播机制，并基于历史ADS-B航迹数据标定扇区服务时间，确定扇区流体排队系统的主要输入参数，实现系统运行状态在不同层级间的映射与并行推演。最后，以全国250个机场、287个扇区和航季级航班运行数据为样本，在航班时刻配置、次日飞行计划及突发容量下降三类场景中开展验证。结果表明，异构Agent模型在各场景中的预测精度均优于现有方法，能够在战略、预战术及战术决策阶段实现“航班-机场-空域”一体化的供需态势分析，能够为航空交通系统的规划、评估与运行管控提供可靠、准确且高效的决策支撑。
In the air traffic system, different decision-making stages lack a unified modeling tool for supply–demand situation assessment, making it difficult to support multi-level and multi-stage collaborative decision-making. To address this issue, this study develops a unified modeling framework for air traffic network supply–demand situations based on heterogeneous agents. First, the theoretical analysis demonstrates that the completeness of the airspace network structure has a decisive impact on the accuracy of delay characterization, and clarifies the functional relationship between network node completeness and prediction error. Then, by integrating the agent interaction mechanism with fluid queuing theory, a dynamic multi-element coupling framework covering flights, airports, and airspace is constructed. Three types of heterogeneous agents, flight, airport, and sector, are defined to establish state transition and congestion/delay propagation mechanisms. Based on historical ADS-B trajectory data, sector service times are calibrated, and the main input parameters of the sector fluid queuing system are determined, enabling the mapping and parallel simulation of system operating states across multiple levels. Using data from 250 airports, 287 sectors, and seasonal flight schedules across China, the model is validated in three representative scenarios: flight schedule configuration, next-day flight planning, and sudden capacity degradation. The results show that the heterogeneous-agent model achieves higher prediction accuracy than existing methods in all scenarios, realizing an integrated “flight-airport-airspace” supply–demand analysis across strategic, pre-tactical, and tactical decision-making stages, and providing a reliable, accurate, and efficient decision-support tool for air traffic system planning, evaluation, and operational management.
[1] 杨磊, 张洪海, 胡明华. 广义空中交通流建模综述[J]. 科学技术与工程, 2020, 20 (02): 432-444.
YANG L, ZHANG H H, HU M H. A review of generalized air traffic flow modeling[J]. Science Technology and Engineering, 2020, 20 (2): 432-444. (in Chinese)
[2] RIBEIRO N A, TAY J, NG W, et al. Delay predictive analytics for airport capacity management[J]. Transportation Research Part C: Emerging Technologies, 2025, 171: 104947.
[3] HANSEN M. Micro-level analysis of airport delay externalities using deterministic queuing models: a case study [J]. Journal of air transport management, 2002, 8(2): 73-87.
[4] PYRGIOTIS N, MALONE K M, ODONI A. Modelling delay propagation within an airport network[J]. Transportation Research Part C: Emerging Technologies, 2013, 27: 60-75.
[5] WONG J-T, TSAI S-C. A survival model for flight delay propagation[J]. Journal of Air Transport Management, 2012, 23: 5-11.
[6] FLEURQUIN P, RAMASCO J J, EGUILUZ V M. Systemic delay propagation in the US airport network[J]. Scientific reports, 2013, 3(1): 1159.
[7] AHMADBEYGI S, COHN A, GUAN Y, et al. Analysis of the potential for delay propagation in passenger airline networks[J]. Journal of air transport management, 2008, 14(5): 221-36.
[8] 李明捷, 黄欣宁, 吕晨辉, 等. 基于排队网络模型的机场航班延误预测[J]. 科学技术与工程, 2023, 23(27): 11886-91.
LI M J, HUANG X N, LV C H, el al. Airport Flight Delay Prediction Based on Queuing Network Model[J]. Science Technology and Engineering, 2023, 23(27): 11886-91. (in Chinese)
[9] 王春政, 胡明华, 杨磊, 等. 基于Agent模型的机场网络延误预测[J]. 航空学报, 2021, 42(07): 452-65.
WANG C Z, HU M H, YANG L, et al. Airport network delay prediction based on Agent model[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(07): 452-65. (in Chinese)
[10] 王春政. 机场网络延误态势感知与时隙配置方法研究[D]. 南京: 南京航空航天大学, 2023: 30-42.
WANG C Z. Research on Airport Network Delay Situation Awareness and Slot Allocation Method [D]. Nan'jing: Nanjing University of Aeronautics and Astronautics, 2023: 30-42. (in Chinese)
[11] 王春政, 胡明华, 杨磊, 等. 空中交通延误预测研究综述[J]. 系统工程与电子技术, 2022, 44(03): 863-874.
WANG C Z, HU M H, YANG L, et al. Review on air traffic delay prediction[J]. Systems Engineering and Electronics, 2022, 44(03): 863-874. (in Chinese)
[12] REBOLLO J J, BALAKRISHNAN H. Characterization and prediction of air traffic delays[J]. Transportation research part C: Emerging technologies, 2014, 44: 231-241.
[13] BIROLINI S, JACQUILLAT A. Day-ahead aircraft routing with data-driven primary delay predictions[J]. European Journal of Operational Research, 2023, 310(1): 379-396.
[14] KHANMOHAMMADI S, TUTUN S, KUCUK Y. A new multilevel input layer artificial neural network for predicting flight delays at JFK airport[J]. Procedia Computer Science, 2016, 95: 237-244.
[15] LIN Y, LI L, REN P, et al. From aircraft tracking data to network delay model: A data-driven approach considering en-route congestion[J]. Transportation Research Part C: Emerging Technologies, 2021, 131: 103329.
[16] TU Y, BALL M O, JANK W S. Estimating flight departure delay distributions—a statistical approach with long-term trend and short-term pattern[J]. Journal of the American Statistical Association, 2008, 103(481): 112-125.
[17] CHOUDHURY A, BASAK A. Statistical inference on traffic intensity in an M/M/1 queueing system[J]. International Journal of Management Science and Engineering Management, 2018, 13(4): 274-279.
[18] 叶博嘉. 基于多Agent的空中交通协同流量管理研究[D]. 南京: 南京航空航天大学, 2013: 16-23.
YE B J. Research on Collaborative Air Traffic Flow Management Based upon Multi-Agent Modeling and Simulation[D]. Nan'jing: Nanjing University of Aeronautics and Astronautics, 2013: 16-23. (in Chinese)
[19] SIEGFRIED R. Grams-General Reference Model for Agent-based Modeling and Simulation[M]. Modeling and Simulation of Complex Systems: A Framework for Efficient Agent-Based Modeling and Simulation. Springer. 2014: 75-110.
[20] 中国民用航空局. 航班正常管理规定[S]. 北京: 中国民用航空局政策法规司, 2016.
C A A C. Regulations on Normal Flight Management[S]. Policy and Regulation Department of Civil Aviation Administration of China. Beijing. 2016. (in Chinese).
[21] WHITT W. Fluid models for multiserver queues with abandonments[J]. Operations Research, 2006, 54(1): 37-54.
[22] CAMPELLO R J, MOULAVI D, ZIMEK A, et al. Hierarchical density estimates for data clustering, visualization, and outlier detection[J]. ACM Transactions on Knowledge Discovery from Data, 2015, 10(1): 1-51.
[23] SALVADOR S, CHAN P. Toward accurate dynamic time warping in linear time and space[J]. Intelligent data analysis, 2007, 11(5): 561-80.
[24] SENIN P. Dynamic time warping algorithm review[J]. Information and Computer Science Department University of Hawaii at Manoa Honolulu, USA, 2008, 855(1-23): 40.
[25] SILVERMAN B W. Density estimation for statistics and data analysis[M]. Routledge, 2018.
[26] 中国民用航空局. 中国民航国内航空资料汇编(NAIP)[G].空中交通管理局. 北京. 2023.
Civil Aviation Administration of China. The China Aeronautical Information Publication (NAIP)[G]. Air Traffic Management Bureau. Beijing. 2023. (in Chinese).
[27] LIU P-C B, HANSEN M, MUKHERJEE A. Scenario-based management of air traffic flow: developing and using capacity scenario trees[J]. Transportation research record, 2006, 1951(1): 113-121.
[28] 中国民用航空局空中交通管理局. 2023年民航空域发展报告 [R]. 北京, 2024.
AIR TRAFFIC MANAGEMENT BUREAU, C A A C. 2023 Civil Aviation Airspace Development Report[R]. Beijing, 2024. (in Chinese)
[29] 中国民用航空局. 民用航空空中交通流量管理暂行规定: 第三章 流量管理要求 [S]. 北京, 2023.
Civil Aviation Administration of China. Interim Provisions on Civil Aviation Air Traffic Flow Management: Chapter III Requirements for Flow Management [S]. Beijing, 2023. (in Chinese)
CJA