期刊文献+

大型分布式仿真环境下的负载平衡策略

Load balance strategy in large scale distributed simulation environment
下载PDF
导出
摘要 在大型分布式仿真环境下,仿真的顺利推进取决于每一个邦员的健康运行,负载不平衡会对仿真性能造成严重的影响。作为分布式仿真事实上的标准,HLA仿真框架主要关注于解决分布式仿真的互操作和可重用问题,而没有提供对可伸缩性、动态负载平衡以及容错的支持。通过分析HLA仿真框架的不足,提出了一个基于网格服务的先进分布式仿真框架GADS,并在此基础上设计了一个负载平衡解决方案,随后重点描述了其中的负载平衡策略和基于仿真代理的高效邦员迁移算法。利用在GADS框架中引入的仿真代理层,该迁移方案大大降低了迁移开销,并实现了真正的"免冻结"迁移。 As the IEEE 1516 standard for distribution simulation,High Level Architecture(HLA) framework does not solve the issues of scalability,dynamic load-balance and fault tolerance.HLA does not support federation migration,which would balance the system workload on heterogeneous distributed resources and consequently improve simulation’s performance.In this paper,a Grid based Advanced Distributed Simulation(GADS) framework is proposed.Based on the GADS framework, this paper proposes a highly efficient load balance strategy and a federate migration protocol by utilizing grid computing.A simulation broker layer is introduced which is in charge of the federates’communication with the other simulation federates. Experiment shows that this approach decreases the migration overhead,improves the performance of the simulations in large-scale distributed environments,and realizes the"freeze-free"migration.
出处 《计算机工程与应用》 CSCD 北大核心 2011年第9期25-28,36,共5页 Computer Engineering and Applications
基金 国家部委2009年度预研基金
关键词 高级体系结构(HLA) 分布式仿真 邦员迁移 仿真代理 网格计算 High Level Architecture (HLA) distributed simulation federate migration simulation broker grid computing
  • 相关文献

参考文献15

  • 1Zajac K, Bubak M,Malawski M, et al.Exeeution and migration management of hlabased interactive simulations on the grid[C]// PPAM, 2003 : 872-879.
  • 2Luthi J, Grossmann S.The resource sharing system:Dynamic federate mapping for hlabased distributed simulation[C]//PADS' 01 : Proceedings of the 15th Workshop on Parallel and Distributed Simulation,Washington DC,USA,2001:91-98.
  • 3Cai W,Tttrner S J,Zhao H.A load management system for running hlabased distributed simulations over the grid[C]//DSRT'02: Proceedings of the 6th IEEE International Workshop on Distributed Simulation and RealTime Applications, Washington DC, USA, 2002.
  • 4Chen D,Turner S J, Cai W.A framework for robust HLAbased distributed simulations[C]//Proceedings of 20th IEEE/ACM/SCS Workshop on Principles of Advanced and Distributed Simulation (PADS 2006).[S.I.]:IEEE Computer Society,2006:183-192.
  • 5Li Zengxiang,Cai Wentong,Turner S J,et al.Federate migration in a service oriented HLA RTI[C]//llth IEEE International Symposium on Distributed Simulation and Real-Time Applications(DSRT 2007) ,2007 : 113-121.
  • 6Tan G, Persson A,Ayani R.HLA federate migration[C]//Proceedhags of the 38th Annual Simulation Symposium(ANSS05),Washington, USA, 2005 : 243-250.
  • 7Boukerche A,De Grande R E.Optimized federate migration for largescale HLAbased Simulations[C]//Proceedings of the 12th IEEE/ACM International Symposium on Distributed Simulation and RealTime Applications, 2008 : 227-239.
  • 8李飞,杨放春,苏森.分布式Web服务QoS注册中的高效负载均衡方法[J].电子与信息学报,2009,31(5):1022-1025. 被引量:3
  • 9Tan G, Lim K C.Load distribution services in hla[C]//Proceedings of the 8th IEEE International Symposium on Distributed Simulation and RealTime Applications, 2004: 133-141.
  • 10Yuan Z,Cai W,Low M Y H,et al.Federate migration in hlabased simulation[C]/AVorkshop on HLABased Distributed Simulation on the Grid in the 4th International Conferenee Computational Science(ICCS 2004),Krakw,Poland,2004:856-864.

二级参考文献9

  • 1Koloniari G and Pitoura E. Peer-to-peer management of XML data : Issues and research challenges. ACM SIGMOD Record, 2005, 34(2): 6-17.
  • 2Schmidt C and Parashar M. A peer-to-peer approach to Web service discovery. Proceedings of the 13th International Conference on World Wide Web, New York, NY, USA (2004) 211-229.
  • 3Chafle G, Chandra S, and Kankar P, et al.. Handling faults in decentralized orchestration of composite Web services. Proceedings of the 3rd International Conference on Service Oriented Computing, ICSOC'05, 2005, LNCS 3826: 410-423.
  • 4Benatallah B, Sheng Q, and Dumas M. The Self-serv environment for Web services composition. Internet Computing, 2003, 7(1): 40-48.
  • 5Gibelin N and Makpangou M. Efficient and transparent Web-services selection. Proceedings of the 3th International Conference on Service Oriented Computing, 2005, LNCS 3826: 527-532.
  • 6Li F, Yang F C, and Shuang K, et al.. Q-Peer: A decentralized QoS registry architecture for Web services. Proceedings of International Conference on Service-Oriented Computing (ICSOC), 2007, LNCS 4749: 145-156.
  • 7LI F, Yang F C, and Shuang K, et al.. Peer-to-Peer based QoS registry architecture for Web services. Proceedings of the 7th IFIP International Conference on Distributed Applications and Interoperable Systems, DAIS'07, 2007, LNCS 4531: 133-138.
  • 8Napster Homepage, http://www.napster.com.
  • 9Adamic L A and Huberman B A. Zipf's Law and the Internet, Glottometrics, 3, 2002: 143-150.

共引文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部