Advertisement

Towards a Non-intrusive Recognition of Anomalous System Behavior in Data Centers

  • Roberto Baldoni
  • Adriano Cerocchi
  • Claudio Ciccotelli
  • Alessandro Donno
  • Federico Lombardi
  • Luca Montanari
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8696)

Abstract

In this paper we propose a monitoring system of a data center that is able to infer when the data center is getting into an anomalous behavior by analyzing the power consumption at each server and the data center network traffic. The monitoring system is non-intrusive in the sense that there is no need to install software on the data center servers. The monitoring architecture embeds two Elman Recurrent Networks (RNNs) to predict power consumed by each data center component starting from data center network traffic and viceversa. Results obtained along six mounts of experiments, within a data center, show that the architecture is able to classify anomalous system behaviors and normal ones by analyzing the error between the actual values of power consumption and network traffic and the ones inferred by the two RNNs.

Keywords

monitoring failure prediction dependability critical infrastructure data centers power consumption network traffic non-intrusive black box 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Over s.r.l. website, http://www.overtechnologies.com
  2. 2.
    Encog Machine Learning Framework (2008), http://www.heatonresearch.com/encog/
  3. 3.
    Aguilera, M.K., Mogul, J.C., Wiener, J.L., Reynolds, P., Muthitacharoen, A.: Performance debugging for distributed systems of black boxes. SIGOPS Oper. Syst. Rev. 37, 74–89 (2003)CrossRefGoogle Scholar
  4. 4.
    Aniello, L., Baldoni, R., Bonomi, S., Lombardi, F., Zelli, A.: An Architecture for Automatic Scaling of Replicated Services. To appear in the Proceedings of the 2nd International Conference on NETworked sYStems (NETYS), vol. 5 (2014)Google Scholar
  5. 5.
    Baldoni, R., Caruso, M., Cerocchi, A., Ciccotelli, C., Montanari, L., Nicoletti, L.: Correlating power consumption and network traffic for improving data centers resiliency. ArXiv e-prints (May 2014)Google Scholar
  6. 6.
    Baldoni, R., Lodi, G., Montanari, L., Mariotta, G., Rizzuto, M.: Online black-box failure prediction for mission critical distributed systems. In: Ortmeier, F., Lipaczewski, M. (eds.) SAFECOMP 2012. LNCS, vol. 7612, pp. 185–197. Springer, Heidelberg (2012)Google Scholar
  7. 7.
    Frank, R.J., Davey, N., Hunt, S.P.: Time series prediction and neural networks. Journal of Intelligent and Robotic Systems 31(1-3), 91–103 (2001)CrossRefzbMATHGoogle Scholar
  8. 8.
    Heller, B., Seetharaman, S., Mahadevan, P., Yiakoumis, Y., Sharma, P., Banerjee, S., McKeown, N.: Elastictree: Saving energy in data center networks. In: Proceedings of the 7th USENIX Conference on Networked Systems Design and Implementation, NSDI 2010, p. 17. USENIX Association, Berkeley (2010)Google Scholar
  9. 9.
    Kazandjieva, M., Heller, B., Levis, P., Kozyrakis, C.: Energy dumpster diving. In: SOSP 2009: Proceedings of the ACM SIGOPS 22nd Symposium on Operating Systems Principles. ACM, New York (2009)Google Scholar
  10. 10.
    Lefurgy, C., Wang, X., Ware, M.: Power capping: A prelude to power shifting. Cluster Computing 11(2), 183–195 (2008)CrossRefGoogle Scholar
  11. 11.
    Park, D.C., El-Sharkawi, M.A., Marks, R.J., Atlas, L.E., Damborg, M.J., et al.: Electric load forecasting using an artificial neural network. IEEE Transactions on Power Systems 6(2), 442–449 (1991)CrossRefGoogle Scholar
  12. 12.
    Riedmiller, M., Braun, H.: A direct adaptive method for faster backpropagation learning: The rprop algorithm. In: IEEE International Conference on Neural Networks, pp. 586–591. IEEE (1993)Google Scholar
  13. 13.
    Senjyu, T., Takara, H., Uezato, K., Funabashi, T.: One-hour-ahead load forecasting using neural network. IEEE Transactions on Power Systems 17(1), 113–118 (2002)CrossRefGoogle Scholar
  14. 14.
    Tan, Y., Gu, X., Wang, H.: Adaptive system anomaly prediction for large-scale hosting infrastructures. In: Proc. of ACM PODC 2010, pp. 173–182. ACM, New York (2010)Google Scholar
  15. 15.
    Wang, X., Yao, Y., Wang, X., Lu, K., Cao, Q.: Carpo: Correlation-aware power optimization in data center networks. In: 2012 Proceedings IEEE INFOCOM, pp. 1125–1133 (March 2012)Google Scholar
  16. 16.
    Wang, X., Chen, M.: Cluster-level feedback power control for performance optimization. In: IEEE 14th International Symposium on High Performance Computer Architecture, HPCA 2008, pp. 101–110 (February 2008)Google Scholar
  17. 17.
    Wang, X., Wang, Y.: Co-con: Coordinated control of power and application performance for virtualized server clusters. In: 17th International Workshop on Quality of Service, IWQoS, pp. 1–9 (July 2009)Google Scholar
  18. 18.
    Williams, A.W., Pertet, S.M., Narasimhan, P.: Tiresias: Black-box failure prediction in distributed systems. In: Proceedings of IEEE International Parallel and Distributed Processing Symposium (IPDPS 2007), Los Alamitos, CA, USA (2007)Google Scholar
  19. 19.
    Zhang, G., Patuwo, B.E., Hu, M.Y.: Forecasting With Artificial Neural Networks: the State of the Art. International Journal of Forecasting 14(1), 35–62 (1998)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Roberto Baldoni
    • 1
  • Adriano Cerocchi
    • 2
  • Claudio Ciccotelli
    • 1
  • Alessandro Donno
    • 1
  • Federico Lombardi
    • 1
  • Luca Montanari
    • 1
  1. 1.Cyber Intelligence and Information Security Research Center“Sapienza” University of RomeRomeItaly
  2. 2.Over TechnologiesRomeItaly

Personalised recommendations