论文

异构舰载机舰面保障作业动态并行调度

  • 陈旭东 ,
  • 陈琦琦 ,
  • 罗祎喆 ,
  • 王佳宝 ,
  • 徐明亮
展开
  • 1.郑州大学 计算机与人工智能学院,郑州 450001
    2.智能集群系统教育部工程研究中心,郑州 450001
    3.国家超级计算郑州中心,郑州 450001
.E-mail: luoyizhe@zzu.edu.cn

收稿日期: 2024-09-30

  修回日期: 2024-11-20

  录用日期: 2025-01-16

  网络出版日期: 2025-02-10

基金资助

国家自然科学基金(62325602);国家自然科学基金(62406292);国家自然科学基金(62036010)

Dynamic parallel scheduling of heterogeneous carrier-based aircraft deck support operations

  • Xudong CHEN ,
  • Qiqi CHEN ,
  • Yizhe LUO ,
  • Jiabao WANG ,
  • Mingliang XU
Expand
  • 1.School of Computer and Artificial Intelligence,Zhengzhou University,Zhengzhou 450001,China
    2.Engineering Research Center of Intelligent Swarm Systems,Ministry of Education,Zhengzhou 450001,China
    3.National Supercomputing Center in Zhengzhou,Zhengzhou 450001,China

Received date: 2024-09-30

  Revised date: 2024-11-20

  Accepted date: 2025-01-16

  Online published: 2025-02-10

Supported by

National Natural Science Foundation of China(62325602)

摘要

针对航母舰载机舰面保障作业被抽象为柔性流水车间调度问题后多项作业(工件)难以并行处理的问题,以及现有研究在处理异构舰载机保障作业协同调度方面的局限性,提出了一种决策模型中央调度模块与深度强化学习决策模型相结合的动态并行调度方法。首先,将并行的舰载机保障作业时间序列等效转化为串行的逻辑序列,使其适配于柔性流水车间调度问题模型的同时保证作业并行执行的特征;然后,基于逻辑序列构建作业调度决策的马尔可夫模型,结合有人机和无人机的作业流程差异,分别为其设计并训练决策模型;同时,设计决策模型中央调度模块对2类决策模型进行统一管理,统筹全局阵位、资源、舰载机等态势信息,并下发至各决策模型以对其进行有效协同。最后,仿真对比实验显示,相较于以遗传算法为代表的优化计算调度方法,所提算法可在牺牲微小调度性能的情况下大幅提升决策实时性,兼顾了舰载机出动时间和调度方法产出时间,更适用于强实时、高动态环境下的舰载机快速出动任务。

本文引用格式

陈旭东 , 陈琦琦 , 罗祎喆 , 王佳宝 , 徐明亮 . 异构舰载机舰面保障作业动态并行调度[J]. 航空学报, 2025 , 46(13) : 531329 -531329 . DOI: 10.7527/S1000-6893.2024.31329

Abstract

In response to the challenge of parallel processing of multiple tasks (workpieces) in carrier-based air-craft support operations, which are abstracted as a flexible flow workshop scheduling problem, and the limitations of existing research in the collaborative scheduling of heterogeneous carrier-based aircraft, a dynamic parallel scheduling method that integrates a central scheduling mechanism with a deep reinforcement learning decision model is proposed. Initially, the parallel time series of support operations is equivalently transformed into a serial logical sequence. This transformation ensures compatibility with the flexible flow workshop scheduling model while preserving the characteristic of parallel execution. Subsequently, a Markov model for job scheduling decisions is constructed based on the logical sequences, incorporating the operational differences between manned and unmanned aerial vehicles. Distinct decision models are designed and trained for each type of aircraft. Moreover, a central scheduling mechanism is developed to unify the management of these two decision models, coordinating global positioning, resources, and other situational information. This mechanism disseminates information to the respective decision models to facilitate effective collaboration. Finally, simulation comparison experiments indicate that the proposed algorithm significantly enhances decision real-time performance, even at the cost of marginal scheduling efficiency, compared to optimization methods represented by genetic algorithms. The algorithm effectively balances carrier-based aircraft deployment time and the output time of scheduling methods, making it particularly suitable for rapid deployment tasks in high-real-time and dynamic environments.

参考文献

[1] 周晓光, 冯百胜, 迟志艳, 等. 基于闭排队网络的舰载机出动架次率分析[J]. 兵工自动化201433(4): 79-83.
  ZHOU X G, FENG B S, CHI Z Y, et al. Analysis of carrier-borne aircraft sortie generation rate based on closed queuing network[J]. Ordnance Industry Automation201433(4): 79-83 (in Chinese).
[2] 司维超, 韩维, 史玮韦. 基于PSO算法的舰载机舰面布放调度方法研究[J]. 航空学报201233(11): 2048-2056.
  SI W C, HAN W, SHI W W. Research on deck-disposed scheduling method of carrier planes based on PSO algorithm[J]. Acta Aeronautica et Astronautica Sinica201233(11): 2048-2056 (in Chinese).
[3] HUANG R, WEN W S, ZHOU Z, et al. Dynamic task offloading for multi-UAVs in vehicular edge computing with delay guarantees: A consensus ADMM-based optimization[J]. IEEE Transactions on Mobile Computing202423(12): 13696-13712.
[4] PARK G, LEE W, LEE K. 3D multi-trajectory and pick-up optimization of UAV for minimizing delivery time with weight restriction[J]. IEEE Transactions on Intelligent Transportation Systems202425(11): 17562-17573.
[5] WANG X, WANG Y, ZHAO J G, et al. Joint long-term user scheduling and beamforming design for burst IIoT?[J]. IEEE Internet of Things Journal202411(12): 22628-22642.
[6] 薛松, 陈旭, 汪玉亭, 等. 基于改进多种群遗传算法的多目标资源受限项目调度问题研究[J]. 管理工程学报202337(5): 167-175.
  XUE S, CHEN X, WANG Y T, et al. Research on multi-objective resource-constrained project scheduling problem based on improved multi-population genetic algorithm?[J]. Journal of Industrial Engineering and Engineering Management202337(5): 167-175 (in Chinese).
[7] 朱云冲, 梁彦刚, 黎克波, 等. 基于PSO和RRT的智能弹群任务分配算法[J].航空学报202344(S1): 727354.
  ZHU Y C, LIANG Y G, LI K B, et al. Task assignment algorithm for intelligent missile swarm based on PSO and RRT[J]. Acta Aeronautica et Astronautica Sinica202344(S1): 727354 (in Chinese) .
[8] 伍国华, 王天宇. 基于自适应模拟退火的大规模星座测控资源调度算法[J]. 航空学报202344(12): 327759.
  WU G H, WANG T Y. Large-scale constellation TT & C resource scheduling algorithm based on adaptive simulated annealing[J]. Acta Aeronautica et Astronautica Sinica202344(12): 327759 (in Chinese).
[9] Ryan J C, Banerjee A G, Cummings M L, et al. Comparing the performance of expert user heuristics and an inte-ger linear program in aircraft carrier deck operations[J]. IEEE Transactions on Cybernetics201344(6): 761-773.
[10] 李经, 孙哲, 李梦龙, 等. 舰载机保障作业调度决策研究[J]. 舰船电子工程201838(12): 165-168, 184.
  LI J, SUN Z, LI M L, et al. Research on carrier-based aircraft deck operation scheduling[J]. Ship Electronic Engineering201838(12): 165-168, 184 (in Chinese).
[11] LIU J, HAN W, LI J, et al. Integration design of sortie scheduling for carrier aircrafts based on hybrid flexible flowshop?[J]. IEEE Systems Journal202014(1): 1503-1511.
[12] 孟杨凯, 王正, 范加利. 基于禁忌算法对不确定性舰载机保障的调度优化研究[J]. 系统仿真学报202133(10): 2363-2371.
  MENG Y K, WANG Z, FAN J L. Scheduling optimization research based on tabu algorithm for uncertainty carrier aircraft support[J]. Journal of System Simulation202133(10): 2363-2371 (in Chinese).
[13] 刘玉杰, 万兵, 苏析超, 等. 基于IABC算法的舰载机着舰调度[J]. 控制与决策202237(7): 1810-1818.
  LIU Y J, WAN B, SU X C, et al. Scheduling of landing for carrier-based aircraft based on improved artificial bee colony algorithm?[J]. Control and Decision202237(7): 1810-1818 (in Chinese).
[14] 苏析超, 伍恒, 崔荣伟, 等. 基于边际-人工蜂群算法的舰载机机群出动保障人员配置-调度联合优化方法[J]. 北京航空航天大学学报202046(11): 2056-2068.
  SU X C, WU H, CUI R W, et al. Joint optimization method for carrier-based aircraft fleet sortie support personnel configuration and scheduling based on marginal-ABC algorithm[J]. Journal of Beijing University of Aeronautics and Astronautics202046(11): 2056-2068 (in Chinese).
[15] 刘玉杰, 韩维, 苏析超, 等. 基于改进灰狼优化算法的舰载机着舰调度[J]. 北京航空航天大学学报202450(3): 803-813.
  LIU Y J, HAN W, SU X C, et al. Carrier aircraft landing scheduling problem based on improved gray wolf optimization[J]. Journal of Beijing University of Aeronautics and Astronautics202450(3): 803-813 (in Chinese).
[16] 朱兴动, 赵洋, 范加利, 等. 基于改进引力搜索算法的舰载机一站式保障作业优化调度方法[J]. 舰船电子工程202343(8): 98-103, 196.
  ZHU X D, ZHAO Y, FAN J L, et al. Optimization and scheduling method for shipborne aircraft one-stop support operations based on improved gravity search algorithm[J]. Ship Electronic Engineering202343(8): 98-103, 196 (in Chinese).
[17] 李亚飞, 吴庆顺, 徐明亮, 等. 基于强化学习的舰载机保障作业实时调度方法[J]. 中国科学: 信息科学202151(2): 247-262.
  LI Y F, WU Q S, XU M L, et al. Real-time scheduling for carrier-borne aircraft support operations: a reinforcement learning approach[J]. Scientia Sinica (Informationis)202151(2): 247-262 (in Chinese).
[18] LI Y F, WU Q S, HUANG X, et al. Efficient adaptive matching for real-time city express delivery?[J]. IEEE Transactions on Knowledge and Data Engineering202335(6): 5767-5779.
[19] 于彤彤. 基于深度强化学习的舰载机在线调度方法与应用研究[D]. 北京: 北京工业大学, 2020.
  YU T T. Research on online scheduling method and application of carrier-based aircraft based on deep reinforcement learning[D]. Beijing: Beijing University of Technology, 2020 (in Chinese).
[20] FENG H F, ZENG W. Deep reinforcement learning for carrier-borne aircraft support operation scheduling?[C]?∥2021 International Conference on Intelligent Computing, Automation and Applications (ICAA). Piscataway: IEEE Press, 2021.
[21] 冯强, 曾声奎, 康锐. 基于MAS的舰载机动态调度模型[J]. 航空学报200930(11): 2119-2125.
  FENG Q, ZENG S K, KANG R. A MAS-based model for dynamic scheduling of carrier aircraft[J]. Acta Aeronautica et Astronautica Sinica200930(11): 2119-2125 (in Chinese).
[22] FENG Q, LI S J, SUN B. A multi-agent based intelligent configuration method for aircraft fleet maintenance personnel[J]. Chinese Journal of Aeronautics201427(2): 280-290.
[23] HAO H J, ZHANG X Q, CHI Y, et al. Cooperative carrier aircraft support operation scheduling via multi-agent reinforcement learning?[C]?∥2023 24th IEEE International Conference on Mobile Data Management (MDM). Piscataway: IEEE Press, 2023.
[24] WANG N J, MENG X L, LIU Q H, et al. High level architecture based simulation for aircraft carrier deck operations[C]∥2016 IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC). Piscataway: IEEE Press, 2016.
[25] REN T, NIU J W, DAI B, et al. Enabling efficient scheduling in large-scale UAV-assisted mobile-edge computing via hierarchical reinforcement learning?[J]. IEEE Internet of Things Journal20229(10): 7095-7109.
[26] LUO Y Z, WANG Y F, LEI Y L, et al. Decentralized user allocation and dynamic service for multi-UAV-enabled MEC system[J]. IEEE Transactions on Vehicular Technology202473(1): 1306-1321.
[27] Hu Y, Li J, Li X, et al. Knowledge-guided agent-tactic-aware learning for StarCraft micromanagement. Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI). Menlo Park: AAAI Press, 2018.
文章导航

/