浏览全部资源
扫码关注微信
1. 西安建筑科技大学信息与控制工程学院,陕西 西安 710399
2. 陕西师范大学物理学与信息技术学院,陕西 西安 710119
3. 西安电子科技大学通信工程学院,陕西 西安 710071
[ "刘润滋(1988− ),女,山东潍坊人,博士,西安建筑科技大学副教授,主要研究方向为无线网络、空间网络中的资源管理和性能分析" ]
[ "马天赐(1997− ),男,河南洛阳人,西安建筑科技大学硕士生,主要研究方向为数据中继网络任务动态调度" ]
[ "吴伟华(1988− ),男,河北石家庄人,博士,陕西师范大学副研究员,主要研究方向为无线资源分配、人工智能、随机网络优化及其在LTE-U网络中的应用" ]
[ "要趁红(1982− ),女,河南开封人,博士,西安建筑科技大学讲师,主要研究方向为无线中继网络" ]
[ "杨清海(1976− ),男,山东高密人,博士,西安电子科技大学教授,主要研究方向为自主通信、内容交付网络和LET-A技术等" ]
网络出版日期:2023-07,
纸质出版日期:2023-07-25
移动端阅览
刘润滋, 马天赐, 吴伟华, 等. 基于分层强化学习的中继卫星网络任务动态调度方法[J]. 通信学报, 2023,44(7):207-217.
Runzi LIU, Tianci MA, Weihua WU, et al. Dynamic task scheduling method for relay satellite networks based on hierarchical reinforcement learning[J]. Journal on communications, 2023, 44(7): 207-217.
刘润滋, 马天赐, 吴伟华, 等. 基于分层强化学习的中继卫星网络任务动态调度方法[J]. 通信学报, 2023,44(7):207-217. DOI: 10.11959/j.issn.1000-436x.2023130.
Runzi LIU, Tianci MA, Weihua WU, et al. Dynamic task scheduling method for relay satellite networks based on hierarchical reinforcement learning[J]. Journal on communications, 2023, 44(7): 207-217. DOI: 10.11959/j.issn.1000-436x.2023130.
摘 要:近年来,随着各类紧急任务数量的不断增长,如何在控制对常规任务影响的同时保障系统的收益已成为中继卫星网络任务动态调度的巨大挑战。针对这一问题,以最大化紧急任务总收益和最小化常规任务破坏程度为目标,提出了一种基于分层强化学习的中继卫星网络任务动态调度方法。具体而言,为了兼顾系统的长期与短期性能,设计了由上、下级DQN实现的双层调度框架,上级DQN从长期性能出发决定临时优化目标,下级DQN根据优化目标决定当前任务的调度策略。仿真结果表明,与传统的深度学习方法以及部分处理动态调度问题的启发式方法相比,所提方法能够在降低常规任务破坏程度的同时提升紧急任务总收益。
In recent years
with the increasing number of various emergency tasks
how to control the impact on common tasks while ensuring system revenue has become a huge challenge for the dynamic scheduling of relay satellite networks.Aiming at this problem
with the goal of maximizing the total revenue of emergency tasks and minimizing the damage to common tasks
a dynamic task scheduling method for relay satellite networks based on hierarchical reinforcement learning was proposed.Specifically
in order to take into account the long-term and short-term performance of the system at the same time
a two-layer scheduling framework implemented by upper-level and lower-level DQN was designed.The upper-level DQN was responsible for determining the temporary optimization goal based on long-term performance
and the lower-level DQN determined the scheduling strategy for current task according to the optimization goal.Simulation results show that compared with traditional deep learning methods and the heuristic methods dealing with dynamic scheduling problems
the proposed method can improve the total revenue of urgent tasks while reducing the damage to common tasks.
王家胜 . 中国数据中继卫星系统及其应用拓展 [J ] . 航天器工程 , 2013 , 22 ( 1 ): 1 - 6 .
WANG J . China’s data relay satellite system and its application prospect [J ] . Spacecraft Engineering , 2013 , 22 ( 1 ): 1 - 6 .
贺川 , 朱晓敏 , 邱涤珊 . 面向应急成像观测任务的多星协同调度方法 [J ] . 系统工程与电子技术 , 2012 , 34 ( 4 ): 726 - 731 .
HE C , ZHU X M , QIU D S . Cooperative scheduling method of multi-satellites for imaging reconnaissance in emergency condition [J ] . Systems Engineering and Electronics , 2012 , 34 ( 4 ): 726 - 731 .
WU G H , MA M H , ZHU J H , et al . Multi-satellite observation integrated scheduling method oriented to emergency tasks and common tasks [J ] . Journal of Systems Engineering and Electronics , 2012 , 23 ( 5 ): 723 - 733 .
李飞龙 , 李广侠 , 李志强 , 等 . 基于多层分簇的北斗卫星导航系统拓扑结构与路由策略 [J ] . 通信学报 , 2014 , 35 ( 10 ): 31 - 41 .
LI F L , LI G X , LI Z Q , et al . Topology structure and routing policy based on multilayered clusters in Beidou satellite navigation system [J ] . Journal on Communications , 2014 , 35 ( 10 ): 31 - 41 .
HAN S M , BEAK S W , CHO K R , et al . Satellite mission scheduling using genetic algorithm [C ] // Proceedings of 2008 SICE Annual Conference . Piscataway:IEEE Press , 2008 : 1226 - 1230 .
HUI-CHCNG H , JIANG W , LI Y J . Solving on agile satellites mission planning based on tabu search-parallel genetic algorithms [C ] // Proceed ings of 2013 International Conference on Management Science and Proceedings of Engineering 20th Annual Conference Proceedings . Piscataway:IEEE Press , 2013 : 120 - 125 .
HE L J , LI J D , SHENG M , et al . Dynamic scheduling of hybrid tasks with time windows in data relay satellite networks [J ] . IEEE Transactions on Vehicular Technology , 2019 , 68 ( 5 ): 4989 - 5004 .
DENG B Y , JIANG C X , KUANG L L , et al . Two-phase task scheduling in data relay satellite systems [J ] . IEEE Transactions on Vehicular Technology , 2018 , 67 ( 2 ): 1782 - 1793 .
DAI C Q , LI C , FU S , et al . Dynamic scheduling for emergency tasks in space data relay network [J ] . IEEE Transactions on Vehicular Technology , 2021 , 70 ( 1 ): 795 - 807 .
ZHANG Z J , ZHANG N , FENG Z R . Multi-satellite control resource scheduling based on ant colony optimization [J ] . Expert Systems with Applications , 2014 , 41 ( 6 ): 2816 - 2823 .
刘润滋 , 盛敏 , 唐成圆 , 等 . 基于任务拆分聚合的中继卫星系统任务规划方法 [J ] . 通信学报 , 2017 , 38 ( S1 ): 110 - 117 .
LIU R Z , SHENG M , TANG C Y , et al . Tasking planning based on task splitting and merging in relay satellite network [J ] . Journal on Communications , 2017 , 38 ( S1 ): 110 - 117 .
ZHU X M , SIM K M , JIANG J Q , et al . Agent-based dynamic scheduling for earth-observing tasks on multiple airships in emergency [J ] . IEEE Systems Journal , 2016 , 10 ( 2 ): 661 - 672 .
ROJANASOONTHON S , BARD J . A GRASP for parallel machine scheduling with time windows [J ] . INFORMS Journal on Computing , 2005 , 17 ( 1 ): 32 - 51 .
ZHOU D , SHENG M , LI J D , et al . Aerospace integrated networks innovation for empowering 6G:a survey and future challenges [J ] . IEEE Communications Surveys & Tutorials , 2023 , 25 ( 2 ): 975 - 1019 .
LUO S , ZHANG L X , FAN Y S . Dynamic multi-objective scheduling for flexible job shop by deep reinforcement learning [J ] . Computers &Industrial Engineering , 2021 ,159:107489.
0
浏览量
396
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构