SCIENTIA SINICA Informationis, Volume 51 , Issue 9 : 1438(2021) https://doi.org/10.1360/SSI-2020-0117

Reliability concept drift online measurement for composite cloud systems

More info
  • ReceivedMay 3, 2020
  • AcceptedSep 4, 2020
  • PublishedSep 13, 2021


Funded by




[1] Huhns M N, Singh M P. Service-oriented computing: Key concepts and principles. IEEE Internet computing, 2005, 9: 75-81. Google Scholar

[2] Papazoglou M P, van den Heuvel W J. Service oriented architectures: approaches, technologies and research issues. VLDB J, 2007, 16: 389-415 CrossRef Google Scholar

[3] Bouguettaya A, Singh M, Huhns M. A service computing manifesto. Commun ACM, 2017, 60: 64-72 CrossRef Google Scholar

[4] Ye Z, Bouguettaya A, Zhou X. Economic model-driven cloud service composition. ACM Transactions on Internet Technology (TOIT), 2014, 14: 1-19. Google Scholar

[5] Blake M B, Huhns M N. Web-scale workflow: Integrating distributed services. IEEE Internet computing, 2008, 12: 55-59. Google Scholar

[6] Duan W X, Hu M, Zhou Q, et al. Reliability in Cloud Computing System: A Review (in Chinese). Journal of Computer Research and Development, 2020, 57: 102-123. Google Scholar

[7] Jamshidi M. System of systems engineering: innovations for the twenty-first century: John Wiley & Sons, 2011. Google Scholar

[8] Peng K L, Huang C Y. Reliability Analysis of On-Demand Service-Based Software Systems Considering Failure Dependencies. IEEE Trans Serv Comput, 2017, 10: 423-435 CrossRef Google Scholar

[9] Xue X, Wang S, Zhang L. Evaluating of dynamic service matching strategy for social manufacturing in cloud environment. Future Generation Comput Syst, 2019, 91: 311-326 CrossRef Google Scholar

[10] Lu J, Liu A, Dong F, Gu F, Gama J, Zhang G. Learning under Concept Drift: A Review. IEEE Transactions on Knowledge and Data Engineering, 2019, 31: 2346-2363. Google Scholar

[11] Zhao P, Wang X, Xie S, Guo L, Zhou Z H. Distribution-free one-pass learning. IEEE Transactions on Knowledge and Data Engineering (early access article), 2019 pp: 1-1. Google Scholar

[12] Bai L, Du H, Wang W. A novel evolving data stream clustering method based on optimization model. Sci Sin-Inf, 2017, 47: 1464-1482 CrossRef Google Scholar

[13] Zheng Z, Lyu M R, Wang H. Service fault tolerance for highly reliable service-oriented systems: an overview. Science China Information Sciences, 2015, 58: 1-12. Google Scholar

[14] Zheng Z, Lyu M R. Collaborative Reliability Prediction of Service-Oriented Systems, In Proceedings of International Conference on Software Engineering (ICSE), Cape Town, South Africa, 2010. 35-44. Google Scholar

[15] Wang H, Wang L, Yu Q. Online Reliability Prediction via Motifs-Based Dynamic Bayesian Networks for Service-Oriented Systems. IIEEE Trans Software Eng, 2017, 43: 556-579 CrossRef Google Scholar

[16] Salfner F, LENK M, Malek M. A Survey of Online Failure Prediction Methods. ACM Computing Surveys, 2010, 42: Article 10. Google Scholar

[17] ANSI/IEEE. IEEE standard glossary of software engineering terminology. ANSI/IEEE STD-610.12-1990, 1990. https://ieeexplore.ieee.org/document/159342. Google Scholar

[18] Yamada S, Ohba M, Osaki S. S-Shaped Reliability Growth Modeling for Software Error Detection. IEEE Transactions on Reliability, 1983, 32: 475-484. Google Scholar

[19] Brosch F, Koziolek H, Buhnova B, Reussner R. Architecture-Based Reliability Prediction with the Palladio Component Model. IEEE Transactions on Software Engineering, 2011, 38: 1319 - 1339. Google Scholar

[20] Wang L. Architecture-Based Reliability-Sensitive Criticality Measure for Fault-Tolerance Cloud Applications. IEEE Trans Parallel Distrib Syst, 2019, 30: 2408-2421 CrossRef Google Scholar

[21] Cuturi M. Sinkhorn distances: Lightspeed computation of optimal transport, In Proceedings of neural information processing systems 2013, Lake Tahoe, Nevada, United States, 2013. 2292-2300. Google Scholar

[22] Peyré G, Cuturi M. Computational Optimal Transport: With Applications to Data Science: now, 2019. Google Scholar

[23] Al-Masri E and Mahmoud Q H. Investigating web services on the world wide web, In Proceedings of 17th international conference on World Wide Web (WWW), Beijing, China, 2008. 795-804. Google Scholar

[24] Jiang W. Lee D, Hu S. Large-scale longitudinal analysis of soap-based and restful web services. In Proceedings of 19th International Conference on Web Services (ICWS), Honolulu, HI, USA, 2012. 218-225. Google Scholar

  • Figure 1

    Optimal transport problem

  • Figure 2

    (Color online) Performance comparison for different approaches. (a) Accuracy; (b) precision; (c) hit rates;protectłinebreak (d) F1-score

  • Table 1   Aggregation functions of paPoFod for composition cloud systems
    Composite structure Aggregation function
    Sequence or parallel ${{\lambda~}_{\Phi~}}~=~1-\prod\nolimits_{i=1}^{n}{(1-{{\lambda~}_{i}})}$
    Branch ${{\lambda~}_{\Phi~}}~=~1-\sum\nolimits_{i=1}^{n}{{{b}_{i}}(1-{{\lambda~}_{i}})}$
    Loop ${{\lambda~}_{\Phi~}}~=~1-{{\sum\nolimits_{i=0}^{n}{{{l}_{i}}(1-{{\lambda~}_{1}})}}^{i}}$

    Algorithm 1 RCD-SD

    Require:$M\in\mathbb{R}_{+}^{n\times~n}$, $\xi$, $h$, $o$, $\delta~$, MaxIteration.


    Initialize $K$ by solving Eq. (13);

    Initialize $u=[1/n,1/n,\ldots,1/n]_n$;

    while $d\le~{\rm~MaxIteration}$ and $u$ changes do

    Update $u$ by solving Eq. (12);


    end while

    Calculate $v$ by solving Eq. (15);

    Calculate ${{P}^{\xi~}}$ by solving Eq. (11);

    Return ${{P}^{\xi~}}$.

  • Table 2   Impact of $\xi$ ($\kappa~=0.2$)
    $\xi~~=~0.1$ $\xi~~=~0.2$ $\xi~~=~0.3$ $\xi~~=~0.4$ $\xi~~=~0.5$ $\xi~~=~0.6$ $\xi~~=~0.7$ $\xi~=~0.8$ $\xi~~=~0.9$
    Accuracy (%) 88.27 87.8586.94 83.14 79.7674.2669.4463.4658.23
    Precision (%) 42.8742.2641.8839.5737.4234.9231.2227.33 23.38
    Hit rates (%) 89.9288.2487.4584.8781.3375.43 70.2265.1759.83
    F1-score (%) 58.0557.1456.6353.9751.25 47.7343.2238.51 33.62
  • Table 3   Impact of $\kappa~$ ($\xi=0.3$)
    $\kappa~~=~0.1$ $\kappa~~=~0.2$ $\kappa~~=~0.3$ $\kappa~~=~0.4$ $\kappa~~=~0.5$ $\kappa~~=~0.6$ $\kappa~=~0.7$ $\kappa~~=~0.8$ $\kappa~~=~0.9$
    Accuracy (%) 86.0186.1686.1585.7382.3873.9266.4661.1556.37
    Precision (%) 42.0741.8841.2340.9236.1335.5332.6729.6326.88
    Hit rates (%) 88.1187.4586.2285.5584.6380.2075.1468.97 60.43
    F1-score (%) 56.9456.6355.7855.3650.6449.2445.5341.45 37.20

Contact and support