Classification-Based Reputation Mechanism for Master-Worker Computing System

  • Kun Lu
  • Jingchao Yang
  • Haoran Gong
  • Mingchu Li
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 234)


Master-worker computing is a parallel computing scheme, which makes master and worker collaborate. Due to its high reliability availability and serviceability, it is widely used in scientific computing fields. However, lack of cooperation and malicious attack in Master-worker computing can greatly reduce the efficiency of parallel computing. In this paper, we consider a reputation system based on individual classification to inducing worker nodes returning true answer and separate malicious worker nodes. By introducing reinforcement learning, rational workers are induced to behave cooperatively and auditing rate of the master decreases. Our model is based on evolutionary game theory. Simulation results show that our reputation system can not only effectively guarantee eventual correctness, separate malicious worker nodes, but also save the master node’s auditing cost.


Node classification Reinforcement learning Reputation system 


  1. 1.
    Korpela, E.J., et al.: SETI@home-massively distributed computing for SETI. Comput. Sci. Eng. 3(1), 78–83 (2001)CrossRefGoogle Scholar
  2. 2.
    Amazonas Mechanical Turk.
  3. 3.
    Goux, J.P., et al.: An enabling framework for master-worker applications on the computational grid, vol. 4(1), pp. 43–50 (2000)Google Scholar
  4. 4.
    Anta, A.F., Georgiou, C., Mosteiro, M.A., Pareja, D.: Multi-round master-worker computing: a repeated game approach. In: 2016 IEEE 35th Symposium on Reliable Distributed Systems (SRDS), pp. 31–40. IEEE, September 2016Google Scholar
  5. 5.
    Christoforou, E., Anta, A.F., Georgiou, C., Mosteiro, M.A.: Algorithmic mechanisms for reliable master-worker internet-based computing. IEEE Trans. Comput. 63(1), 179–195 (2014)MathSciNetCrossRefzbMATHGoogle Scholar
  6. 6.
    Nguyen, T.T.H., Brun, O., Prabhu, B.J.: Performance of a fixed reward incentive scheme for two-hop DTNs with competing relays: short talk. ACM SIGMETRICS Perform. Eval. Rev. 44(3), 39 (2017)CrossRefGoogle Scholar
  7. 7.
    Seregina, T., Brun, O., El-Azouzi, R., Prabhu, B.J.: On the design of a reward-based incentive mechanism for delay tolerant networks. IEEE Trans. Mob. Comput. 16(2), 453–465 (2017)CrossRefGoogle Scholar
  8. 8.
    Lu, K., Wang, S., Xie, L., Wang, Z., Li, M.: A dynamic reward-based incentive mechanism: reducing the cost of P2P systems. Knowl. Based Syst. 112, 105–113 (2016)CrossRefGoogle Scholar
  9. 9.
    Gupta, R., Somani, A.K.: Game theory as a tool to strategize as well as predict nodes’ behavior in peer-to-peer networks. In: International Conference on Parallel and Distributed Systems (2005)Google Scholar
  10. 10.
    Orset, J.M., Ana, C.: Security in ad hoc networks. In: Ad Hoc Networking Towards Seamless Communications. Springer Netherlands, pp. 756–775 (2002)Google Scholar
  11. 11.
    Ciccarelli, G., Cigno, R.L.: Collusion in peer-to-peer systems. Comput. Netw. 55(15), 3517–3532 (2011)CrossRefGoogle Scholar
  12. 12.
    Christoforou, E., Anta, A.F., Georgiou, C., Mosteiro, Miguel A., Sánchez, A.: Reputation-based mechanisms for evolutionary master-worker computing. In: Baldoni, R., Nisse, N., van Steen, M. (eds.) OPODIS 2013. LNCS, vol. 8304, pp. 98–113. Springer, Cham (2013). Scholar
  13. 13.
    Sonnek, J., Chandra, A., Weissman, J.: Adaptive reputation- based scheduling on unreliable distributed infrastructures. IEEE Trans. Parallel Distrib. Syst. 18(11), 1551–1564 (2007)CrossRefGoogle Scholar
  14. 14.
    BONIC reputation platform.
  15. 15.
    Kondo, D., et al.: Characterizing result errors in internet desktop grids. In: European Conference on Parallel Processing, pp. 361–371 (2007)Google Scholar

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2018

Authors and Affiliations

  • Kun Lu
    • 1
  • Jingchao Yang
    • 1
  • Haoran Gong
    • 1
  • Mingchu Li
    • 1
  1. 1.School of Software TechnologyDalian University of TechnologyDalianChina

Personalised recommendations