Workload time series prediction in storage systems: a deep learning based approach | Cluster Computing Skip to main content

Advertisement

Springer Nature Link
Log in

Workload time series prediction in storage systems: a deep learning based approach

  • Published:
Cluster Computing Aims and scope Submit manuscript

Abstract

Storage workload prediction is a critical step for fine-grained load balancing and job scheduling in realtime and adaptive cluster systems. However, how to perform workload time series prediction based on a deep learning method has not yet been thoroughly studied. In this paper, we propose a storage workload prediction method called CrystalLP based on deep learning. CrystalLP includes workload collecting, data preprocessing, time series prediction, and data post-processing phase. The time series prediction phase is based on a long short-term memory network (LSTM). Furthermore, to improve the efficiency of LSTM, we study the sensitivity of the hyperparameters in LSTM. Extensive experimental results show that CrystalLP can obtain performance improvement compared with three classic time series prediction algorithms.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Notes

  1. http://traces.cs.umass.edu/index.php/Storage/Storage.

References

  1. Abbasi, M., Shokrollahi, A.: Enhancing the performance of decision tree-based packet classification algorithms using CPU cluster. Clust. Comput. pp. 1–17 (2020)

  2. Ahmad, I., Khalil, M.I.K., Shah, S.A.A.: Optimization-based workload distribution in geographically distributed data centers: a survey. Int. J. Commun. Syst. p. e4453 (2020)

  3. Azizi, S., Li, D., et al.: An energy-efficient algorithm for virtual machine placement optimization in cloud data centers. Clust. Comput. pp. 1–14 (2020)

  4. Bengio, Y., Delalleau, O., Roux, N.L.: The curse of dimensionality for local kernel machines. Tech. Rep. (2006)

  5. Box, G.E.P., Jenkins, G.M.: Time series analysis, forecasting and control, holden-day. J. R. Stat. Soc. 134(3), 229–240 (1976)

    Google Scholar 

  6. Chen, Z., Hu, J., Min, G., Zomaya, A.Y., El-Ghazawi, T.: Towards accurate prediction for high-dimensional and highly-variable cloud workloads with deep learning. IEEE Trans. Parallel Distribut. Syst. 31(4), 923–934 (2019)

    Article  Google Scholar 

  7. Di, S., Kondo, D., Cirne, W.: Host load prediction in a google compute cloud with a bayesian model. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, p. 21. IEEE Computer Society Press (2012)

  8. Dong, B., Li, X., Wu, Q., Xiao, L., Li, R.: A dynamic and adaptive load balancing strategy for parallel file system with large-scale i/o servers. J. Parallel Distribut. Comput. 72(10), 1254–1268 (2012)

    Article  Google Scholar 

  9. Duggan, M., Shaw, R., Duggan, J., Howley, E., Barrett, E.: A multitime-steps-ahead prediction approach for scheduling live migration in cloud data centers. Softw. Pract. Exp. 49(4), 617–639 (2019)

    Article  Google Scholar 

  10. Firoz, J.S., Zalewski, M., Lumsdaine, A., Barnas, M.: Runtime scheduling policies for distributed graph algorithms. In: IEEE International Parallel and Distributed Processing Symposium, pp. 640–649 (2018)

  11. Gao, J., Wang, H., Shen, H.: Task failure prediction in cloud data centers using deep learning. IEEE Trans. Serv. Comput. pp. 1–1 (2020). https://doi.org/10.1109/TSC.2020.2993728

  12. Geng, X., Zhang, H., Zhao, Z., Ma, H.: Interference-aware parallelization for deep learning workload in GPU cluster. Clust. Comput. pp. 1–14 (2020)

  13. Gupta, S., Dileep, A.D., Gonsalves, T.A.: Online sparse blstm models for resource usage prediction in cloud datacentres. In: IEEE Transactions on Network and Service Management pp. 1–1 (2020)

  14. Hamilton, J.D.: Time series analysis, vol. 2. Princeton University Press Princeton, NJ (1994)

  15. Huang, Z., Peng, J., Lian, H., Guo, J., Qiu, W.: Deep recurrent model for server load and performance prediction in data center. Complexity 2017(99), 1–10 (2017)

    Article  MATH  Google Scholar 

  16. Jassas, M.S., Mahmoud, Q.H.: Failure characterization and prediction of scheduling jobs in google cluster traces. In: 2019 IEEE 10th GCC Conference & Exhibition (GCC), pp. 1–7. IEEE (2019)

  17. Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. Comput. Sci. (2014)

  18. Kumar, J., Singh, A.K.: Workload prediction in cloud using artificial neural network and adaptive differential evolution. Future Generat. Comput. Syst. 81, 41–52 (2018)

    Article  Google Scholar 

  19. Lu, Y., Sun, N.: An effective task scheduling algorithm based on dynamic energy management and efficient resource utilization in green cloud computing environment. Clust. Comput. 22(1), 513–520 (2019)

    Article  MathSciNet  Google Scholar 

  20. Masdari, M., Khoshnevis, A.: A survey and classification of the workload forecasting methods in cloud computing. Clust. Comput. pp. 1–26 (2019)

  21. Neelima, P., Reddy, A.R.M.: An efficient load balancing system using adaptive dragonfly algorithm in cloud computing. Clust. Comput. pp. 1–9 (2020)

  22. Oral, S., Simmons, J., Hill, J., Leverman, D., Wang, F., Ezell, M., Miller, R., Fuller, D., Gunasekaran, R., Kim, Y., Gupta, S., Vazhkudai, D.T.S.S., Rogers, J.H., Dillow, D., Shipman, G.M., Bland, A.S.: Best practices and lessons learned from deploying and operating large-scale data-centric parallel file systems. In: SC ’14: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 217–228 (2014)

  23. Pang, P., Chen, Q., Zeng, D., Guo, M.: Adaptive preference-aware co-location for improving resource utilization of power constrained datacenters. IEEE Trans. Parallel Distribut. Syst. 32(2), 441–456 (2020)

    Article  Google Scholar 

  24. Peng, C., Li, Y., Yu, Y., Zhou, Y., Du, S.: Multi-step-ahead host load prediction with gru based encoder-decoder in cloud computing. In: 2018 10th International Conference on Knowledge and Smart Technology (KST), pp. 186–191. IEEE (2018)

  25. Ping, L.: Analysis and development of the locality principle. Adv. Intell. Soft Comput. 133(7), 211–214 (2012)

    Article  Google Scholar 

  26. Sundermeyer, M., Ney, H.: From Feedforward to Recurrent LSTM Neural Networks for Language Modeling. IEEE Press, Oxford (2015)

    Book  Google Scholar 

  27. Tang, K., Huang, P., He, X., Lu, T., Vazhkudai, S.S., Tiwari, D.: Toward managing HPC burst buffers effectively: draining strategy to regulate bursty i/o behavior. In: 2017 IEEE 25th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS), pp. 87–98 (2017)

  28. Tang, X., Liao, X., Zheng, J., Yang, X.: Energy efficient job scheduling with workload prediction on cloud data center. Clust. Comput. 21(3), 1581–1593 (2018)

    Article  Google Scholar 

  29. Wang, B., Wang, C., Song, Y., Cao, J., Cui, X., Zhang, L.: A survey and taxonomy on workload scheduling and resource provisioning in hybrid clouds. Clust. Comput. pp. 1–26 (2020)

  30. Xia, B., Li, T., Zhou, Q.F., Li, Q., Zhang, H.: An effective classification-based framework for predicting cloud capacity demand in cloud services. In: IEEE Transactions on Services Computing (2018)

  31. Xu, M., Buyya, R.: Brownout approach for adaptive management of resources and applications in cloud computing systems: A taxonomy and future directions. ACM Comput. Surv. 52(1), 26–41 (2019). https://doi.org/10.1145/3234151

    Article  Google Scholar 

  32. Yu, Y., Jindal, V., Bastani, F., Li, F., Yen, I.L.: Improving the smartness of cloud management via machine learning based workload prediction. In: 2018 IEEE 42nd Annual Computer Software and Applications Conference (COMPSAC), vol. 2, pp. 38–44. IEEE (2018)

  33. Zhang, H., Geng, X., Ma, H.: Learning-driven interference-aware workload parallelization for streaming applications in heterogeneous cluster. IEEE Trans. Parallel Distribut. Syst. 32(1), 1–15 (2020)

    Article  Google Scholar 

  34. Zhang, Q., Yang, L.T., Yan, Z., Chen, Z., Li, P.: An efficient deep learning model to predict cloud workload for industry informatics. IEEE Trans Indust. Inform. 14(7), 3170–3178 (2018)

    Article  Google Scholar 

  35. Zhang, Z., Tang, X., Han, J., Wang, P.: Sibyl: Host load prediction with an efficient deep learning model in cloud computing. In: Algorithms and Architectures for Parallel Processing-18th International Conference, ICA3PP 2018, Guangzhou, China, November 15-17, 2018, Proceedings, Part II, pp. 226–237 (2018)

Download references

Acknowledgements

This work is by supported by the National Key R&D Program of China under Grant No. 2017YFB0202004, the National Science Foundation of China under Grant No. 61772053, the fund of the State Key Laboratory of Software Development Environment under Grant No. SKLSDE-2020ZX-15.

Author information

Authors and Affiliations

  1. State Key Laboratory of Software Development Environment, Beihang University, Beijing, 100191, China

    Li Ruan, Yu Bai, Shaoning Li & Limin Xiao

  2. School of Computer Science and Engineering, Beihang University, Beijing, 100191, China

    Li Ruan, Yu Bai, Shaoning Li & Limin Xiao

  3. College of Computer Science and Technology, Zhejiang University, Zhejiang, 310027, China

    Shuibing He

Authors
  1. Li Ruan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yu Bai
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shaoning Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shuibing He
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Limin Xiao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Li Ruan.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ruan, L., Bai, Y., Li, S. et al. Workload time series prediction in storage systems: a deep learning based approach. Cluster Comput 26, 25–35 (2023). https://doi.org/10.1007/s10586-020-03214-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10586-020-03214-y

Keywords

Search

Navigation