Online Reliability Time Series Prediction for Service-Oriented System of Systems

  • Lei Wang
  • Hongbing Wang
  • Qi Yu
  • Haixia Sun
  • Athman Bouguettaya
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8274)


A Service-Oriented System of System (or SoS) considers system as a service and constructs a value-added SoS by outsourcing external systems through service composition. To cope with the dynamic and uncertain running environment and assure the overall Quality of Service (or QoS), online reliability prediction for SoS arises as a grand challenge in SoS research. In this paper, we propose a novel approach for component level online reliability time series prediction based on Probabilistic Graphical Models (or PGMs). We assess the proposed approach via invocation records collected from widely used real web services and experiment results demonstrate the effectiveness of our approach.


Response Time Service Composition Probabilistic Graphical Model Conditional Probability Table Service Invocation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Cook, T.S., Drusinksy, D., Shing, M.T.: Specification, validation and run-time monitoring of soa based system-of-systems temporal behaviors. In: IEEE International Conference on System of Systems Engineering, SoSE 2007, pp. 1–6. IEEE (2007)Google Scholar
  2. 2.
    Koller, D., Friedman, N.: Probabilistic graphical models: principles and techniques. MIT press (2009)Google Scholar
  3. 3.
    Lelli, F., Maron, G., Orlando, S.: Client side estimation of a remote service execution. In: 15th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 2007, pp. 295–302. IEEE (2007)Google Scholar
  4. 4.
    Mansour, H.E., Dillon, T.: Dependability and rollback recovery for composite web services. IEEE Transactions on Services Computing 4(4), 328–339 (2011)CrossRefGoogle Scholar
  5. 5.
    Rothenhaus, K.J., Michael, J.B., Shing, M.T.: Architectural patterns and auto-fusion process for automated multisensor fusion in soa system-of-systems. IEEE Systems Journal 3(3), 304–316 (2009)CrossRefGoogle Scholar
  6. 6.
    Salfner, F., Lenk, M., Malek, M.: A survey of online failure prediction methods. ACM Computing Surveys 42(3), 10:1–10:42 (2010)Google Scholar
  7. 7.
    Shellman, E.R., Burant, C.F., Schnell, S.: Network motifs provide signatures that characterize metabolism. Molecular BioSystems 9(3), 352–360 (2013)CrossRefGoogle Scholar
  8. 8.
    Yu, Q.: Decision tree learning from incomplete qos to bootstrap service recommendation. In: Proc. 19th IEEE International Conference on Web Services, ICWS 2012, pp. 194–201 (2012)Google Scholar
  9. 9.
    Yu, Q.: Qos-aware service selection via collaborative qos evaluation. World Wide Web Journal (accepted to appear, 2013)Google Scholar
  10. 10.
    Yu, Q., Zheng, Z., Wang, H.: Trace norm regularized matrix factorization for service recommendation. In: Proc. 20th IEEE International Conference on Web Services, ICWS 2013 (2013)Google Scholar
  11. 11.
    Zheng, Z., Lyu, M.R.: Collaborative reliability prediction of service-oriented systems. In: Proceedings of the 32nd ACM/IEEE International Conference on Software Engineering, ICSE 2010, pp. 35–44. ACM (2010)Google Scholar
  12. 12.
    Zheng, Z., Ma, H., Lyu, M., King, I.: Collaborative web service qos prediction via neighborhood integrated matrix factorization (early access articles). IEEE Transactions on Services Computing (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Lei Wang
    • 1
    • 2
  • Hongbing Wang
    • 1
  • Qi Yu
    • 3
  • Haixia Sun
    • 1
  • Athman Bouguettaya
    • 4
  1. 1.School of Computer Science and EngineeringSoutheast UniversityChina
  2. 2.Dept. of Management Science and EngineeringNanjing Forestry UniversityChina
  3. 3.College of Computing and Information SciencesRochester Institute of TechUSA
  4. 4.School of Computer Science and Information TechnologyRMITAustralia

Personalised recommendations