面向空间操控仿真的任务调度微服务策略

doi:10.12305/j.issn.1001-506X.2023.05.15

摘要/Abstract

摘要：

针对大型空间操控仿真试验中TB、PB量级的遥测参数、载荷数传等指数性增长的数据交互计算压力, 以及海量多源异构仿真模型的并发调用对传统服务架构带来的挑战, 构建了面向空间操控仿真的任务调度微服务(task scheduling microservice for simulation, S-TSM)解决方案。借助混合式微服务调度技术, 建立以负载迁移模型为核心的双引擎动态任务调度平台, 规避负载均衡震荡并优化服务端节点资源分配, 具备负载平衡周期短、计算任务响应迅速、高吞吐稳定性等优点。通过实地航天器试验仿真系统的实验结果表明, 在满足海量操控仿真任务调度与操控对象交互数据高吞吐处理需求下, S-TSM与Xxl-job、Elastic-job、Spring Cloud任务调度架构相比, 单次业务平均响应时延分别缩短0.10 s、0.25 s、0.92 s, 与轮询、比率、弹性分片等其他负载平衡算法相比, 平均负载平衡耗时缩短1.90 s, 具备一定的竞争力。

关键词: 空间操控仿真, 微服务, 任务调度, 负载平衡

Abstract:

Aiming at the exponentially increasing data interaction computing pressure of TB and PB telemetry parameters, load data transmission and other data in large-scale space manipulation simulation experiments, as well as the challenges to the traditional service architecture brought by the concurrent invocation of massive multi-source heterogeneous simulation models, a task scheduling microservice for simulation (S-TSM) solution for space manipulation simulation is constructed. With the help of hybrid microservice scheduling technology, a dual engine dynamic task scheduling platform with the load migration model as the core is established to avoid load balancing shocks and optimize the resource allocation of server nodes. It has the advantages of short load balancing cycle, rapid computing task response, high throughput stability, etc. The experimental results of the field spacecraft test simulation system show that, under the condition of meeting the requirements of massive control simulation task scheduling and high throughput processing of interactive data of control objects, compared with the Xxl-job, Elastic-job, Spring Cloud task scheduling architecture, the average response time of a single service of S-TSM is shortened by 0.10 s, 0.25 s, 0.92 s respectively, and the average load balancing time is shortened by 1.90 s compared with polling, ratio, elastic sharding and other load balancing algorithms, with certain competitiveness.

Key words: space manipulation simulation, microservice, task scheduling, load balancing

中图分类号:

TP311.5

覃润楠, 谢文明, 惠建江, 彭晓东, 李运. 面向空间操控仿真的任务调度微服务策略[J]. 系统工程与电子技术, 2023, 45(5): 1391-1398.

Runnan QIN, Wenming XIE, Jianjiang HUI, Xiaodong PENG, Yun LI. Task scheduling microservice strategy for space manipulation simulation[J]. Systems Engineering and Electronics, 2023, 45(5): 1391-1398.

图/表 12

图1

图2

图3

图4

图5

表1

图6

表2

图7

图8

图9

表3

参考文献 30

1	Goddard Space Flight Center. On-orbit satellite servicing study project report[R]. Greenbelt: National Aeronautics and Space Administration, 2010: 141-145.
2	苏丽, 张博为, 谌明, 等. 大数据技术在航天领域发展与应用[J]. 遥测遥控, 2015, 36 (2): 1- 9. doi: 10.13435/j.cnki.ttc.002684
	SU L , ZHANG B W , CHEN M , et al. Development and application of big data technology in aerospace field[J]. Journal of Telemetry, Tracking and Command, 2015, 36 (2): 1- 9. doi: 10.13435/j.cnki.ttc.002684
3	WU H Y , DENG W J . Research progress on the development of micro services[J]. Journal of Computer Research and Development, 2020, 57 (3): 525- 541.
4	FENG Z Y , XU Y W , XUE X , et al. Review on the development of micro service architecture[J]. Journal of Computer Research and Development, 2020, 57 (5): 1103- 1122.
5	DRAGONI N, LANESE I, LARSENS T, et al. Micro services: how to make your application scale[C]//Proc. of the International Andrei Earshot Memorial Conference on Perspectives of System Informatics, 2017: 95-104.
6	冯志勇, 徐砚伟, 薛霄, 等. 微服务技术发展的现状与展望[J]. 计算机研究与发展, 2020, 57 (5): 1103- 1122.
	FENG Z Y , XU Y W , XUE X , et al. Current situation and prospect of micro service technology and development[J]. Computer Research and Development, 2020, 57 (5): 1103- 1122.
7	CHRIS R, FLOYD S. Designing and deploying microservices[EB/OL]. [2022-06-21]. https://github.com/DocsHome/microservices.
8	SUN X , CHEN H N , WANG Q Y , et al. Research and design of online training platform based on spring cloud distributed system structure and computer big data[J]. Journal of Physics: Conference Series, 2021, 1952 (4): 042087. doi: 10.1088/1742-6596/1952/4/042087
9	ADRIAN C. State of the art in microservices[EB/OL]. [2022-06-21]. https://blog.docker.com/2014/12/deckercon-enrope-keynote-of-the-art-in-mi-croservices-by-adrian-cockcroft-battery-ventures/.
10	LIANG F. Apache Dubbo[EB/OL]. [2022-06-21]. https://github.com/apache/dubbo.
11	MOHAMMAD R , AMIR M R , MEHDI H . Dependability analysis for characterizing Google cluster reliability[J]. International Journal of Communication Systems, 2019, 3 (16): e4127.
12	THANH T , YEOM Y , KIM T , et al. Horizontal pod autoscaling in kubernetes for elastic container orchestration[J]. Sensors, 2020, 20 (16): 4621. doi: 10.3390/s20164621
13	马武彬, 王锐, 王威超, 等. 基于进化多目标优化的微服务组合部署与调度策略[J]. 系统工程与电子技术, 2020, 42 (1): 90- 100.
	MA W B , WANG R , WANG W C , et al. Micro service composition deployment and scheduling strategy based on evolutionary multi-objective optimization[J]. Systems Engineering and Electronics, 2020, 42 (1): 90- 100.
14	FENG L, JON B. Elastic job bundling: an adaptive resource request strategy for large-scale parallel applications[C]//Proc. of the International Conference on High Performance Computing Networking, Storage and Analysis, 2015.
15	XU X L. A distributed task scheduling framework[EB/OL]. [2022-06-21]. https://github.com/xuxueli/xxl-job.
16	TREVOR M. Spring cloud scheduler[EB/OL]. [2022-06-21]. https://github.com/spring-attic/spring-cloud-scheduler.
17	吴超宇. 面向异构平台的混合任务调度系统设计与实现[D]. 北京: 北京邮电大学, 2020.
	WU C Y. Design and implementation of hybrid task scheduling system for heterogeneous platform[D]. Beijing: Beijing University of Posts and Telecommunications, 2020.
18	陈嘉夫. 一种面向多调度系统支持多任务类型的资源调度平台设计与实现[D]. 西安: 西安电子科技大学, 2021.
	CHEN J F. Design and implementation of a resource scheduling platform supporting multiple scheduling systems and multiple task types[D]. Xi'an: Xidian University, 2021.
19	ASGHARI A , SOHRABI M K . Combined use of coral reefs optimization and reinforcement learning for improving resource utilization and load balancing in cloud environments[J]. Computing, 2021, 103 (7): 1545- 1567. doi: 10.1007/s00607-021-00920-2
20	罗欢, 姜唯, 刘明伟, 等. 基于微服务架构的多资源负载均衡优化方法[J]. 科学技术与工程, 2022, 22 (5): 1965- 1971. doi: 10.3969/j.issn.1671-1815.2022.05.030
	LUO H , JIANG W , LIU M W , et al. Multi resource load balancing optimization method based on micro service architecture[J]. Science Technology and Engineering, 2022, 22 (5): 1965- 1971. doi: 10.3969/j.issn.1671-1815.2022.05.030
21	PENMATSA S , CHRONOPOULO A T . Game-theoretic static load balancing for distributed systems[J]. Journal of Parallel and Distributed Computing, 2011, 71 (4): 537- 555. doi: 10.1016/j.jpdc.2010.11.016
22	KUMAR J , SINGH A K , MOHAN A . Resource-efficient load-balancing framework for cloud data center networks[J]. Journal of Electronics and Telecommunications Research Institute, 2020, 43 (1): 53- 63.
23	WANG W Y , JIANG Y C . Community-aware task allocation for social networked multi-agent systems[J]. IEEE Trans.on Cybernetics, 2014, 44 (9): 1529- 1543. doi: 10.1109/TCYB.2013.2289327
24	JIANG Y C . A survey of task allocation and load balancing in distributed systems[J]. IEEE Trans.on Parallel & Distributed Systems, 2016, 27 (2): 585- 599.
25	路程昭, 龚建兴, 朱雷, 等. 资源约束条件下任务调度算法研究[J]. 系统工程与电子技术, 2021, 43 (12): 3586- 3593.
	LU C Z , GONG J X , ZHU L , et al. Research on task scheduling algorithm in resource-constrained environments[J]. Systems Engineering and Electronics, 2021, 43 (12): 3586- 3593.
26	LOPES R V , DANIEL M . A taxonomy of job scheduling on distributed computing systems[J]. IEEE Trans.on Parallel and Distributed Systems, 2016, 27 (12): 3412- 3428.
27	ALSADIE D . TSMGWO: optimizing task schedule using multi-objectives grey wolf optimizer for cloud data centers[J]. IEEE Access, 2021, 9, 37707- 37725.
28	SAINT L S . Programming web services with XML-RPC[M]. United States: O'Reilly & Associates, 2001.
29	王玉静. 遥感数据处理可视化工作流技术及应用研究[D]. 廊坊: 北华航天工业学院, 2020.
	WANG Y J. Research on visualization workflow technology and application of remote sensing data processing[D]. Langfang: Beihua Institute of Aerospace Technology, 2020.
30	ROSING M V , WHITE S , CUMMINS F , et al. Business process model and notation-BPMN[J]. Complete Business Process Handbook, 2015, 95 (1): 433- 457.

名称	参数配置
名称	数量	性能参数
通用工作站	2	CPU: Intel Core i7-7500 3.4G 内存: 16GB DDR4 硬盘: 2TB 7200RPM 3.5"SATA3
计算服务器	8	CPU: 40core (2.1 GHz) 内存: 8×32GB DDR4 硬盘: 10×1TB 7200RPM

名称	架构时延
	操控对象交互数据包/个			操控仿真任务调度
	1 000	4 000	10 000	轨道	姿态	通信
Xxl-job	0.45	0.55	1.01	0.39	0.25	0.27
Elastic-job	0.65	0.78	1.33	0.44	0.29	0.32
Spring Cloud	1.53	1.65	2.19	1.21	0.56	0.68
S-TSM^*	0.27	0.36	0.85	0.35	0.19	0.28

算法	负载平衡耗时
	操控对象交互数据包/个			操控仿真任务
	1 000	4 000	8 000	轨道	姿态	通信
静态轮询算法	22.23	25.65	30.01	7.88	2.13	2.09
静态比率算法	22.34	25.32	29.93	7.98	2.32	2.25
动态优先权调度算法	21.97	24.76	29.12	7.23	2.08	2.12
动态最少连接调度算法	21.85	24.98	28.98	6.54	1.97	1.75
Xxl-job	19.14	22.08	26.87	5.89	1.45	1.11
Elastic-job	19.43	22.32	26.98	4.98	2.24	1.54
Spring Cloud	20.55	23.23	27.23	4.89	2.05	1.54
S-TSM	18.23	21.56	26.89	3.78	1.34	0.62

[1]	陈韩, 张晶, 董俊, 董洁. 子任务调度和时延联合优化的MEC卸载方案[J]. 系统工程与电子技术, 2023, 45(2): 572-579.
[2]	路程昭, 龚建兴, 朱雷, 刘权. 资源约束条件下任务调度算法研究[J]. 系统工程与电子技术, 2021, 43(12): 3586-3593.
[3]	马武彬, 王锐, 王威超, 吴亚辉, 邓苏, 黄宏斌. 基于进化多目标优化的微服务组合部署与调度策略[J]. 系统工程与电子技术, 2020, 42(1): 90-100.
[4]	李波, 周静杨, 高晓光. 基于拍卖算法的相控阵雷达任务调度方法[J]. 系统工程与电子技术, 2018, 40(8): 1736-1742.
[5]	曾斌, 姚路, 胡炜, 杨光. 考虑不确定因素影响的保障任务调度算法[J]. 系统工程与电子技术, 2016, 38(3): 595-601.
[6]	柳玉, 向东阳, 郑春弟. 面向异构分布式计算环境的并行任务调度优化方法[J]. 系统工程与电子技术, 2016, 38(2): 332-338.
[7]	熊嵩，周军，呼卫军. 基于扩展HLA的作战系统动态平衡仿真[J]. 系统工程与电子技术, 2014, 36(4): 789-794.
[8]	于荣欢, 吴玲达, 邓宝松, 瞿师. 基于ITM的复杂电磁环境并行计算方法[J]. Journal of Systems Engineering and Electronics, 2012, 34(7): 1339-1343.
[9]	赵宇，李建勋，曹兰英，张世仓. 基于二次规划的相控阵雷达任务自适应调度算法[J]. Journal of Systems Engineering and Electronics, 2012, 34(4): 698-703.
[10]	王海波，徐敏强，王日新，李玉庆. 基于IP-ACO算法的航天器测控资源调度技术[J]. Journal of Systems Engineering and Electronics, 2012, 34(4): 719-725.
[11]	陈祥国,武小悦. 任务调度启发式信息的卫星数传ACO算法应用[J]. Journal of Systems Engineering and Electronics, 2010, 32(6): 1251-1257.
[12]	朱海, 王宇平. 安全驱动的实时任务调度遗传算法[J]. Journal of Systems Engineering and Electronics, 2010, 32(4): 854-859.
[13]	陈祥国, 武小悦. 基于解构造图的卫星数传调度ACO算法[J]. Journal of Systems Engineering and Electronics, 2010, 32(3): 592-597.
[14]	马宏星,周学海,高妍妍. 可重构计算平台上软硬件任务划分与调度算法[J]. Journal of Systems Engineering and Electronics, 2010, 32(11): 2459-2464.
[15]	常飞, 武小悦. 基于改进粒子群算法的卫星数传任务调度[J]. Journal of Systems Engineering and Electronics, 2009, 31(10): 2404-2408.