Fault Tolerant Framework in MPI-based Distributed DEVS Simulation

被引:0
|
作者
Chen, Bin [1 ]
Qiu, Xiao-gang [1 ]
Huang, Ke-di [1 ]
机构
[1] Natl Univ Def Technol, Syst Simulat Lab, Sch Mechatron & Automat, Changsha, Hunan, Peoples R China
关键词
DEVS; Fault Tolerance; Fault Detection; States Storage; Fault Recovery;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Distributed DEVS simulation plays an important role in solving complex problems for its reuseability, and composability of component models. Using MPI to be the communication middleware, the distribution increases the performance. But even the tiny faults of computing resources can lead to crash. Hence Fault Tolerant is necessary to maintain the simulation reliability. This paper introduces a DEVS framework supported Fault Tolerant. The optimistic distributed simulators implement the distribution in DEVS simulation. Fault Detection, States Storage and Fault Recovery are integrated into the framework to avoid crash at runtime. Experiments are carried out to find the optimal Timeout for Fault Tolerant framework. The results indicate that the framework has to be adjusted along with the changing of simulation requirements. Keywords: DEVS, Fault Tolerance, Fault Detection, States Storage, Fault Recovery
引用
收藏
页码:866 / 871
页数:6
相关论文
共 50 条
  • [1] MPI-based Distribution in DEVS Simulation
    Chen, Bin
    Qiu, Xiao-gang
    2009 THIRD INTERNATIONAL SYMPOSIUM ON INTELLIGENT INFORMATION TECHNOLOGY APPLICATION, VOL 2, PROCEEDINGS, 2009, : 78 - 81
  • [2] pMIIND-an MPI-based population density simulation framework
    Marc de Kamps
    David Sichau
    BMC Neuroscience, 14 (Suppl 1)
  • [3] An MPI-based tool for distributed genetic programming
    Tomassini, M
    Vanneschi, L
    Bucher, L
    Fernández, F
    CLUSTER 2000: IEEE INTERNATIONAL CONFERENCE ON CLUSTER COMPUTING, PROCEEDINGS, 2000, : 209 - 216
  • [4] An MPI-based framework for processing spatial vector data on heterogeneous distributed systems
    1600, Institute of Electrical and Electronics Engineers Inc., United States
  • [5] An MPI-based Framework for Processing Spatial Vector Data on Heterogeneous Distributed Systems
    Araki, Kouichi
    Shimbo, Taiki
    2016 FOURTH INTERNATIONAL SYMPOSIUM ON COMPUTING AND NETWORKING (CANDAR), 2016, : 554 - 558
  • [6] Modeling and Designing Fault-Tolerance Mechanisms for MPI-based MapReduce Data Computing Framework
    Lin, Jian
    Liang, Fan
    Lu, Xiaoyi
    Zha, Li
    Xu, Zhiwei
    2015 IEEE FIRST INTERNATIONAL CONFERENCE ON BIG DATA COMPUTING SERVICE AND APPLICATIONS (BIGDATASERVICE 2015), 2015, : 176 - 183
  • [7] Exploit Approximation to Support Fault Resiliency in MPI-based Applications
    Rocco, Roberto
    Palermo, Gianluca
    2023 53RD ANNUAL IEEE/IFIP INTERNATIONAL CONFERENCE ON DEPENDABLE SYSTEMS AND NETWORKS WORKSHOPS, DSN-W, 2023, : 187 - 190
  • [8] Fault tolerant distributed simulation
    Lin, Yi-Bing
    Journal of Information Science and Engineering, 1994, 10 (02) : 259 - 269
  • [9] MPI-Based parallel implementation of a lithography pattern simulation algorithm
    Radhakrishna, H
    Divakar, S
    Magotra, N
    Brueck, SRJ
    Waters, A
    HIGH-PERFORMANCE COMPUTING AND NETWORKING, PROCEEDINGS, 1999, 1593 : 109 - 119
  • [10] CORBA AND MPI-BASED "BACKBONE" FOR COUPLING ADVANCED SIMULATION TOOLS
    Seydaliev, M.
    Caswell, D.
    CNL NUCLEAR REVIEW, 2014, 3 (02) : 83 - 90