网络卫星在轨分布式协同任务调度方法
|
摘要
针对网络条件下卫星执行多目标观测任务的自主调度问题,本文设计了一种"Sandwich"空间信息网络体系架构,通过网络传输延时仿真分析,其传输时延为毫秒级别,略优于传统中继方式,该网络传输效能适合多任务需求下实施在轨分布式协同计算;在此基础上,提出了一种分布式断链重连算法,可突破单星计算资源限制,提高在轨计算能力。仿真结果表明:相比单星计算,可有效缩短任务调度约一半时间;利用树莓派和无线网络搭建了分布式调度演示系统,完成了该算法的工程实现。该方法可满足组网状态下面向多任务的各类对地观测、天基探测类卫星的空间在轨自主任务规划调度需求,为空间信息网络的进一步研究和应用奠定技术基础。
This study designs a"sandwich"space information network architecture that aims to solve the problem of multi-object observation satellite scheduling. Simulation results show that the network transmission delay is in milliseconds,which is slightly better than that in traditional relay mode. Therefore,the network transmission performance is suitable for multiple task requirements in implementing on-orbit distributed collaborative computing. At the same time,a distributed broken-chain reconnection scheduling algorithm is proposed,which breaks through the computing resource of the single satellite and improves on-orbit computing capacity. A ground demonstration system with wireless network and Raspberry Pi is built which,according to simulation results,can effectively shorten the task scheduling by approximately half the time compared with the single satellite calculation. This method can be applied to the network autonomous mission planning and scheduling requirements for multi-tasking,earth observation,or space-based detection satellites,thereby laying the technical foundation for further research and application of a space information network.
This study designs a"sandwich"space information network architecture that aims to solve the problem of multi-object observation satellite scheduling. Simulation results show that the network transmission delay is in milliseconds,which is slightly better than that in traditional relay mode. Therefore,the network transmission performance is suitable for multiple task requirements in implementing on-orbit distributed collaborative computing. At the same time,a distributed broken-chain reconnection scheduling algorithm is proposed,which breaks through the computing resource of the single satellite and improves on-orbit computing capacity. A ground demonstration system with wireless network and Raspberry Pi is built which,according to simulation results,can effectively shorten the task scheduling by approximately half the time compared with the single satellite calculation. This method can be applied to the network autonomous mission planning and scheduling requirements for multi-tasking,earth observation,or space-based detection satellites,thereby laying the technical foundation for further research and application of a space information network.
引文
[1]BENSANA E,VERFAILLIE G,AGNSE J C,et al. Exact and approximate methods for the daily management of an earth observation satellite[C]//Proceedings of the 4th International Symposium on Space Mission Operations and Ground Data Systems. Dordrecht:Kluwer Academic,1996.
[2]HALL N G,MAGAZINE M J. Maximizing the value of a space mission[J]. European journal of operational research,1994,78(2):224-241.
[3]MORRIS R A,DUNGAN J L,BRESINA J L. An information infrastructure for coordinating earth science observations[C]//Proceeding of the 2nd IEEE International Conference on Space Mission Challenges for Information Technology. Pasadena:IEEE,2006.
[4]常青,李显旭,何善宝.我国空间信息网发展探讨[J].遥测遥控,2015,36(1):1-10.CHANG Qing,LI Xianxu,HE Shanbao. Confer on the evolution of earth-space integrated information network of China[J]. Journal of telemetry,tracking and command,2015,36(1):1-10.
[5]闵士权.我国天基综合信息网构想[J].航天器工程,2013,22(5):1-14.MIN Shiquan. An idea of China's space-based integrated information network[J]. Spacecraft engineering,2013,22(5):1-14.
[6]ZHANG Keke,XIA Lei,ZHANG Shengyu,et al. Double layer LEO satellite based“BigMAC”space information network architecture[C]//YU Quan. Space Information Networks. Singapore:Springer,688:217-231.
[7]SWEET N,KANEFSKY S. The C2 constellation a us air force network centric warfare program[C]//2004 Command and contral reseach and technology symposium.[S. l.],2004.
[8]FARSEROTU J,PRASAD R. A survey of future broadband multimedia satellite systems,issues and trends[J]. IEEE communications magazine,2000,38(6):128-133.
[9]SURHONE L M,TENNOE M T,HENSSONOW S F. InterPlaNet[M]. Echeveria:Betascript Publishing,2010.
[10]MARTINEZ P,URIBE G G A,MOSQUERA P F L. OneWeb:plataforma de adaptación de contenidos web basada en las recomendaciones del W3C Mobile Web Initiative[J].Ingenieriaéinvestigación,2011,31(1):117-126.
[11]潘志舟.基于任务复制和插入的分布式任务调度算法研究[D].武汉:华中科技大学,2015.PAN Zhizhou. Task-duplication and insertion based scheduling algorithm for heterogeneous computing environments[D]. Wuhan:Huazhong University of Science and Technology,2015.
[2]HALL N G,MAGAZINE M J. Maximizing the value of a space mission[J]. European journal of operational research,1994,78(2):224-241.
[3]MORRIS R A,DUNGAN J L,BRESINA J L. An information infrastructure for coordinating earth science observations[C]//Proceeding of the 2nd IEEE International Conference on Space Mission Challenges for Information Technology. Pasadena:IEEE,2006.
[4]常青,李显旭,何善宝.我国空间信息网发展探讨[J].遥测遥控,2015,36(1):1-10.CHANG Qing,LI Xianxu,HE Shanbao. Confer on the evolution of earth-space integrated information network of China[J]. Journal of telemetry,tracking and command,2015,36(1):1-10.
[5]闵士权.我国天基综合信息网构想[J].航天器工程,2013,22(5):1-14.MIN Shiquan. An idea of China's space-based integrated information network[J]. Spacecraft engineering,2013,22(5):1-14.
[6]ZHANG Keke,XIA Lei,ZHANG Shengyu,et al. Double layer LEO satellite based“BigMAC”space information network architecture[C]//YU Quan. Space Information Networks. Singapore:Springer,688:217-231.
[7]SWEET N,KANEFSKY S. The C2 constellation a us air force network centric warfare program[C]//2004 Command and contral reseach and technology symposium.[S. l.],2004.
[8]FARSEROTU J,PRASAD R. A survey of future broadband multimedia satellite systems,issues and trends[J]. IEEE communications magazine,2000,38(6):128-133.
[9]SURHONE L M,TENNOE M T,HENSSONOW S F. InterPlaNet[M]. Echeveria:Betascript Publishing,2010.
[10]MARTINEZ P,URIBE G G A,MOSQUERA P F L. OneWeb:plataforma de adaptación de contenidos web basada en las recomendaciones del W3C Mobile Web Initiative[J].Ingenieriaéinvestigación,2011,31(1):117-126.
[11]潘志舟.基于任务复制和插入的分布式任务调度算法研究[D].武汉:华中科技大学,2015.PAN Zhizhou. Task-duplication and insertion based scheduling algorithm for heterogeneous computing environments[D]. Wuhan:Huazhong University of Science and Technology,2015.