Journal of Zhejiang University SCIENCE C

, Volume 14, Issue 11, pp 845–858 | Cite as

A mixture of HMM, GA, and Elman network for load prediction in cloud-oriented data centers

  • Da-yu XuEmail author
  • Shan-lin Yang
  • Ren-ping Liu


The rapid growth of computational power demand from scientific, business, and Web applications has led to the emergence of cloud-oriented data centers. These centers use pay-as-you-go execution environments that scale transparently to the user. Load prediction is a significant cost-optimal resource allocation and energy saving approach for a cloud computing environment. Traditional linear or nonlinear prediction models that forecast future load directly from historical information appear less effective. Load classification before prediction is necessary to improve prediction accuracy. In this paper, a novel approach is proposed to forecast the future load for cloud-oriented data centers. First, a hidden Markov model (HMM) based data clustering method is adopted to classify the cloud load. The Bayesian information criterion and Akaike information criterion are employed to automatically determine the optimal HMM model size and cluster numbers. Trained HMMs are then used to identify the most appropriate cluster that possesses the maximum likelihood for current load. With the data from this cluster, a genetic algorithm optimized Elman network is used to forecast future load. Experimental results show that our algorithm outperforms other approaches reported in previous works.

Key words

Cloud computing Load prediction Hidden Markov model Genetic algorithm Elman network 

CLC number



Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Andersson, S., Yamagishi, J., Clark, R.A.J., 2012. Synthesis and evaluation of conversational characteristics in HMM-based speech synthesis. Speech Commun., 54(2):175–188. [doi:10.1016/j.specom.2011.08.001]CrossRefGoogle Scholar
  2. Arasu, A., Manku, G.S., 2004. Approximate Counts and Quantiles over Sliding Windows. 23rd ACM SIGMOD-SIGACT-SIGART Symp. on Principles of Database Systems, p.286–296. [doi:10.1145/1055558.1055598]Google Scholar
  3. Ardagna, D., Casolari, S., Colajanni, M., Panicucci, B., 2012. Dual time-scale distributed capacity allocation and load redirect algorithms for cloud systems. J. Parall. Distr. Comput., 72(6):796–808. [doi:10.1016/j.jpdc.2012.02.014]CrossRefzbMATHGoogle Scholar
  4. Armbrust, M., Fox, A., Griffith, R., Joseph, A.D., Katz, R.H., Konwinski, A., Lee, G., Patterson, D.A., Rabkin, I.S.A., Zaharia, M., 2009. Above the Clouds: a Berkeley View of Cloud Computing. Available from Scholar
  5. Atique, M., Ali, M.S., 2007. A Novel Adaptive Neuro Fuzzy Inference System Based CPU Scheduler for Multimedia Operating System. Int. Conf. on Neural Networks, p.1002–1007. [doi:10.1109/IJCNN.2007.4371095]Google Scholar
  6. Bauer, E., Adams, R., 2012. Reliability and Availability of Cloud Computing. Wiley-IEEE Press, New Jersey, USA.CrossRefzbMATHGoogle Scholar
  7. Bennani, M.N., Menasce, D.A., 2005. Resource Allocation for Autonomic Data Centers Using Analytic Performance Models. 2nd IEEE Int. Conf. on Autonomic Computing, p.229–240. [doi:10.1109/ICAC.2005.50]Google Scholar
  8. Benson, T., Akella, A., Maltz, D.A., 2010. Network Traffic Characteristics of Data Centers in the Wild. 10th ACM SIGCOMM Conf. on Internet Measurement, p.267–280. [doi:10.1145/1879141.1879175]Google Scholar
  9. Bilmes, J., 1997. A Gentle Tutorial on the EM Algorithm and Its Application to Parameter Estimation for Gaussian Mixture and Hidden Markov Models. Technical Report ICSI-TR-97-02, University of Berkeley, CA.Google Scholar
  10. Bozdogan, H., 1987. Model selection and Akaike’s information criterion (AIC): the general theory and its analytical extensions. Psychometrika, 52(3):345–370. [doi:10.1007/BF02294361]MathSciNetCrossRefzbMATHGoogle Scholar
  11. Burnham, K.P., Anderson, D.R., 2004. Multimodel inference understanding AIC and BIC in model selection. Sociol. Methods Res., 33(2):261–304. [doi:10.1177/0049124104268644]MathSciNetCrossRefGoogle Scholar
  12. Calheiros, R.N., Ranjan, R., Buyya, R., 2011. Virtual Machine Provisioning Based on Analytical Performance and QoS in Cloud Computing Environments. Int. Conf. on Parallel Processing, p.295–304. [doi:10.1109/ICPP.2011.17]Google Scholar
  13. Caron, E., Desprez, F., Muresan, A., 2010. Forecasting for Grid and Cloud Computing On-Demand Resources Based on Pattern Matching. 2nd IEEE Int. Conf. on Cloud Computing Technology and Science, p.456–463. [doi:10.1109/CloudCom.2010.65]CrossRefGoogle Scholar
  14. Di, S., Kondo, D., Cirne, W., 2012a. Characterization and Comparison of Cloud versus Grid Workloads. IEEE Int. Conf. on Cluster Computing, p.230–238. [doi:10.1109/CLUSTER.2012.35]Google Scholar
  15. Di, S., Kondo, D., Cirne, W., 2012b. Host Load Prediction in a Google Compute Cloud with a Bayesian Model. IEEE Int. Conf. on High Performance Computing, Networking, Storage and Analysis, p.1–11. [doi:10.1109/SC.2012.68]Google Scholar
  16. Duy, T.V.T., Sato, Y., Inoguchi, Y., 2010. Performance Evaluation of a Green Scheduling Algorithm for Energy Savings in Cloud Computing. IEEE Int. Symp. on Parallel & Distributed Processing, Workshops and PhD Forum, p.1–8. [doi:10.1109/IPDPSW. 2010.5470908]Google Scholar
  17. Duy, T.V.T., Sato, Y., Inoguchi, Y., 2011. Improving accuracy of host load predictions on computational grids by artificial neural networks. Int. J. Parall. Emerg. Distr. Syst., 26(4):275–290. [doi:10.1080/17445760.2010.481786]CrossRefGoogle Scholar
  18. Elman, J., 1990. Finding structure in time. Cogn. Sci., 14(2): 179–211. [doi:10.1207/s15516709cog1402_1]CrossRefGoogle Scholar
  19. Hassan, M.R., Nath, B., Kirley, M., 2007. A fusion model of HMM, ANN and GA for stock market forecasting. Expert Syst. Appl., 33(1):171–180. [doi:10.1016/j.eswa.2006.04.007]CrossRefGoogle Scholar
  20. Hassan, R., Nath, B., Kirley, M., Kamruzzaman, J., 2012. A hybrid of multiobjective evolutionary algorithm and HMM-fuzzy model for time series prediction. Neurocomputing, 81:1–11. [doi:10.1016/j.neucom.2011.09.012]CrossRefGoogle Scholar
  21. Hirose, A., 2012. Complex-Valued Neural Networks, Vol. 400. Springer, New York, Dordrecht, Heidelberg, London.CrossRefzbMATHGoogle Scholar
  22. Islam, S., Keung, J., Lee, K., Liu, A., 2012. Empirical prediction models for adaptive resource provisioning in the cloud. Future Gener. Comput. Syst., 28(1):155–162. [doi:10.1016/j.future.2011.05.027]CrossRefGoogle Scholar
  23. Kaur, P., Soni, A.K., Gosain, A., 2013. A robust kernelized intuitionistic fuzzy c-means clustering algorithm in segmentation of noisy medical images. Pattern Recogn. Lett., 34(2):163–175. [doi:10.1016/j.patrec.2012.09.015]CrossRefGoogle Scholar
  24. Khan, A., Yan, X., Tao, S., Anerousis, N., 2012. Workload Characterization and Prediction in the Cloud: a Multiple Time Series Approach. 3rd IEEE Int. Workshop on Cloud Management, p.1287–1294. [doi:10.1109/NOMS.2012.6212065]Google Scholar
  25. Khashei, M., Zeinal Hamadani, A., Bijari, M., 2012. A novel hybrid classification model of artificial neural networks and multiple linear regression models. Expert Syst. Appl., 39(3):2606–2620. [doi:10.1016/j.eswa.2011.08.116]CrossRefGoogle Scholar
  26. Li, A., Yang, X., Kandula, S., Zhang, M., 2010. CloudCmp: Comparing Public Cloud Providers. 10th ACM SIGCOMM Conf. on Internet Measurement, p.1–14. [doi:10.1145/1879141.1879143]Google Scholar
  27. Liang, K.C., Wang, X.D., Anastassiou, D., 2007. Bayesian basecalling for DNA sequence analysis using hidden Markov models. IEEE Trans. Comput. Biol. Bioinf., 4(3): 430–440. [doi:10.1109/tcbb.2007.1027]Google Scholar
  28. Marston, S., Li, Z., Bandyopadhyay, S., Zhang, J., Ghalsasi, A., 2011. Cloud computing: the business perspective. Decis. Support Syst., 51(1):176–189. [doi:10.1016/j.dss.2010.12.006]CrossRefGoogle Scholar
  29. Mishra, A.K., Hellerstein, J.L., Cirne, W., Das, C.R., 2010. Towards characterizing cloud backend workloads: insights from Google compute clusters. ACM SIGMETRICS Perform. Eval. Rev., 37(4):34–41. [doi:10.1145/1773394.1773400]CrossRefGoogle Scholar
  30. Niu, D.X., Kou, B.E., Zhang, Y.Y., 2009. Mid-long Term Load Forecasting Using Hidden Markov Model. 3rd Int. Symp. on Intelligent Information Technology Application, p.481–483. [doi:10.1109/IITA.2009.422]Google Scholar
  31. Palit, A.K., Popovic, D., 2005. Computational Intelligence in Time Series Forecasting: Theory and Engineering Applications. In: Advances in Industrial Control. Springer-Verlag New York, Inc., Secaucus, NJ.Google Scholar
  32. Prevost, J.J., Nagothu, K., Kelley, B., Jamshidi, M., 2011. Prediction of Cloud Data Center Networks Loads Using Stochastic and Neural Models. 6th Int. Conf. on System of Systems Engineering, p.276–281. [doi:10.1109/SYSOSE.2011.5966610]Google Scholar
  33. Rabiner, L.R., 1989. A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE, 77(2):257–286. [doi:10.1109/5.18626]CrossRefGoogle Scholar
  34. Reiss, C., Tumanov, A., Ganger, G.R., Katz, R.H., Kozuch, M.A., 2012. Towards Understanding Heterogeneous Clouds at Scale: Google Trace Analysis. Proc. 3rd ACM Symp. on Cloud Computing, p.7.Google Scholar
  35. Saripalli, P., Kiran, G.V.R., Shankar, R.R., Narware, H., Bindal, N., 2011. Load Prediction and Hot Spot Detection Models for Autonomic Cloud Computing. 4th IEEE Int. Conf. on Utility and Cloud Computing, p.397–402. [doi:10.1109/UCC.2011.66]CrossRefGoogle Scholar
  36. Vaquero, L.M., Rodero-Merino, L., Caceres, J., Lindner, M., 2009. A break in the clouds: towards a cloud definition. ACM SIGCOMM Comput. Commun. Rev., 39(1):50–55. [doi:10.1145/1496091.1496100]CrossRefGoogle Scholar
  37. Wang, P., Wang, H., Wang, W., 2011. Finding Semantics in Time Series. ACM SIGMOD Int. Conf. on Management of Data, p.385–396. [doi:10.1145/1989323.1989364]Google Scholar
  38. Weakliem, D.L., 1999. A critique of the Bayesian information criterion for model selection. Sociol. Methods Res., 27(3): 359–397. [doi:10.1177/0049124199027003002]CrossRefGoogle Scholar
  39. Yu, L., Wang, S., Lai, K.K., 2008. Credit risk assessment with a multistage neural network ensemble learning approach. Expert Syst. Appl., 34(2):1434–1444. [doi:10.1016/j.eswa.2007.01.009]CrossRefGoogle Scholar
  40. Zhang, G.P., 2003. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50:159–175. [doi:10.1016/S0925-2312(01)00702-0]CrossRefzbMATHGoogle Scholar
  41. Zhang, Y., 2004. Prediction of Financial Time Series with Hidden Markov Models. PhD Thesis, Simon Fraser University, Burnaby, Canada.Google Scholar
  42. Zhang, Y., Sun, W., Inoguchi, Y., 2006. CPU Load Predictions on the Computational Grid. 6th IEEE Int. Symp. on Cluster Computing and the Grid, p.321–326. [doi:10.1109/CCGRID.2006.27]CrossRefGoogle Scholar

Copyright information

© Journal of Zhejiang University Science Editorial Office and Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.MOE Key Laboratory of Process Optimization and Intelligent Decision-MakingHefei University of TechnologyHefeiChina
  2. 2.Information and Communication Technologies CentreCSIROSydneyAustralia

Personalised recommendations