Skip to main content

Advertisement

SpringerLink
Log in

An Integrated Deep Learning Prediction Approach for Efficient Modelling of Host Load Patterns in Cloud Computing

  • Published:
Journal of Grid Computing Aims and scope Submit manuscript

Abstract

Recent surge in technology and integration of IoT into Cloud computing has resulted in increasingly heterogeneous workloads with unprecedented compute and storage demands. As Cloud workloads evolve, so also their computational demands, resulting in server loads interspersed by random peaks and troughs and by continuous and periodic demands. A predictive model that accounts for these diverse load patterns can generate more realistic future resource demands which is essential for efficient capacity planning and meeting service level objectives with minimal energy consumption. Long Short-Term Memory (LSTM), the prevalent approach for host load prediction suffers from information decay with long inputs, while hybrid methods using Convolution Neural Network (CNN) and LSTM fail to effectively model different host load patterns. To overcome above limitations, we propose a multistep CPU usage prediction approach named RCP-CL, to model random fluctuations and novel continuous and periodic patterns from contiguous and non-contiguous CPU load values augmented with daily and weekly time patterns, by integrating 1-Dimensional CNN (1D-CNN) and LSTM networks. RCP-CL uses parallel and stacked 1D-CNN layers with kernel size and dilation rates that are guided by the autocorrelation and partial autocorrelation analysis of CPU usage while LSTM derives temporal dependencies from the learnt spatial patterns. Experimental evaluations with Google Trace and Alibaba trace demonstrate impressive learning skills of RCP-CL over the state-of-the-art LSTM and 1D-CNN based host load prediction models, achieving up to 20% improvement in mean squared error for Google trace and up to 22% improvement for Alibaba trace.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Data availability

The datasets analysed during the current study are available in the Borg Cluster Workload Traces repository, [https://github.com/google/cluster-data/blob/master/ClusterData2011_2.md] and Alibaba Open Cluster Trace Program [https://github.com/alibaba/clusterdata/tree/master/cluster-trace-v2018].

References

  1. Gill, S.S., Xu, M., Ottaviani, C., Patros, P., Bahsoon, R., Shaghaghi, A., … Uhlig, S.: AI for next generation computing: emerging trends and future directions. Internet of Things 19, 100514 (2022). https://doi.org/10.1016/j.iot.2022.100514

  2. Heterogeneous Workloads Require a Comprehensive Portfolio of Infrastructure and Platform Services, May 2021, https://www.oracle.com/a/ocom/docs/cloud/idc-heterogeneous-workloads-oci-brief.pdf?source=WWMK210615P00093. Accessed 10 Oct 2022

  3. Di, S., Kondo, D., Cirne, W.: Characterization and comparison of cloud versus grid workloads. In: 2012 IEEE International Conference on Cluster Computing, pp. 230–238. IEEE (2012). https://doi.org/10.1109/CLUSTER.2012.35

  4. Patel, E., Kushwaha, D.S.: Clustering cloud workloads: K-means vs gaussian mixture model. Procedia Comput. Sci. 171, 158–167 (2020). https://doi.org/10.1016/j.procs.2020.04.017

    Article  Google Scholar 

  5. Duc, T.L., Leiva, R.G., Casari, P., Östberg, P.O.: Machine learning methods for reliable resource provisioning in edge-cloud computing: a survey. ACM Comput. Surv. 52(5), 1–39 (2019). https://doi.org/10.1145/3341145

    Article  Google Scholar 

  6. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997). https://doi.org/10.1007/978-3-642-24797-2_4

    Article  Google Scholar 

  7. Nguyen, H.M., Kalra, G., Kim, D.: Host load prediction in cloud computing using long short-term memory encoder–decoder. J. Supercomput. 75(11), 7592–7605 (2019). https://doi.org/10.1007/s11227-019-02967-7

    Article  Google Scholar 

  8. Patel, E., Kushwaha, D.S.: A hybrid CNN-LSTM model for predicting server load in cloud computing. J. Supercomput. 78(8), 1–30 (2022). https://doi.org/10.1007/s11227-021-04234-0

    Article  Google Scholar 

  9. Song, B., Yu, Y., Zhou, Y., Wang, Z., Du, S.: Host load prediction with long short-term memory in cloud computing. J. Supercomput. 74(12), 6554–6568 (2018). https://doi.org/10.1007/s11227-017-2044-4

    Article  Google Scholar 

  10. Chien, H. Y. S., Turek, J. S., Beckage, N., Vo, V. A., Honey, C. J., Willke, T. L.: Slower is better: revisiting the forgetting mechanism in LSTM for Slower information decay. arXiv preprint arXiv:2105.05944 (2021). https://doi.org/10.48550/arXiv.2105.05944

  11. Herbst, N., Amin, A., Andrzejak, A., Grunske, L., Kounev, S., Mengshoel, O. J., Sundararajan, P.: Online workload forecasting. In: Self-Aware Computing Systems, pp. 529–553. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-47474-8_18

  12. Zhang, Q., Zhani, M. F., Zhang, S., Zhu, Q., Boutaba, R., Hellerstein, J. L.: Dynamic energy-aware capacity provisioning for cloud computing environments. In: Proceedings of the 9th International Conference on Autonomic Computing, pp. 145–154 (2012). https://doi.org/10.1145/2371536.2371562

  13. Calheiros, R.N., Masoumi, E., Ranjan, R., Buyya, R.: Workload prediction using ARIMA model and its impact on cloud applications’ QoS. IEEE Trans. Cloud Comput. 3(4), 449–458 (2014). https://doi.org/10.1109/TCC.2014.2350475

    Article  Google Scholar 

  14. Chehelgerdi-Samani, M., Safi-Esfahani, F.: PCVM. ARIMA: Predictive consolidation of virtual machines applying ARIMA method. J. Supercomput. 77(3), 2172–2206 (2021). https://doi.org/10.1007/s11227-020-03354-3

    Article  Google Scholar 

  15. Debusschere, V., Bacha, S.: Hourly server workload forecasting up to 168 hours ahead using seasonal ARIMA model. In: 2012 IEEE International Conference on Industrial Technology, pp 1127–1131. IEEE  (2012). https://doi.org/10.1109/ICIT.2012.6210091

  16. Wang, S., Li, C., Lim, A.: Why are the ARIMA and SARIMA not sufficient. arXiv preprint arXiv:1904.07632 (2019). https://doi.org/10.48550/arXiv.1904.07632

  17. Moghaddam, S.M., O’Sullivan, M., Walker, C., Piraghaj, S.F., Unsworth, C.P.: Embedding individualized machine learning prediction models for energy efficient VM consolidation within cloud data centers. Futur. Gener. Comput. Syst. 106, 221–233 (2020). https://doi.org/10.1016/j.future.2020.01.008

    Article  Google Scholar 

  18. Banerjee, S., Roy, S., Khatua, S.: Efficient resource utilization using multi-step-ahead workload prediction technique in cloud. J. Supercomput. 1–28 (2021). https://doi.org/10.1007/s11227-021-03701-y

  19. Osypanka, P., Nawrocki, P.: QoS-aware cloud resource prediction for computing services. IEEE Trans. Serv. Comput. (2022). https://doi.org/10.1109/TSC.2022.3164256

    Article  Google Scholar 

  20. 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 Distrib. Syst. 31(4), 923–934 (2019). https://doi.org/10.1109/TPDS.2019.2953745

    Article  Google Scholar 

  21. Goodfellow, I., Bengio, Y., Courville, A.: Deep learning. MIT press (2016)

    MATH  Google Scholar 

  22. Duggan, M., Mason, K., Duggan, J., Howley, E., Barrett, E.: Predicting host CPU utilization in cloud computing using recurrent neural networks. In: 2017 12th International Conference for Internet Technology and Secured Transactions (ICITST), pp. 67–72. IEEE (2017). https://doi.org/10.23919/ICITST.2017.8356348.

  23. Nashold, L., & Krishnan, R.: Using lstm and sarima models to forecast cluster cpu usage. arXiv preprint arXiv:2007.08092 (2020). https://doi.org/10.48550/arXiv.2007.08092

  24. Yang, Q., Zhou, Y., Yu, Y., Yuan, J., Xing, X., Du, S.: Multi-step-ahead host load prediction using autoencoder and echo state networks in cloud computing. J. Supercomput. 71(8), 3037–3053 (2015). https://doi.org/10.1007/s11227-015-1426-8

    Article  Google Scholar 

  25. Cheng, Y., Wang, C., Yu, H., Hu, Y., Zhou, X.: Gru-es: Resource usage prediction of cloud workloads using a novel hybrid method. In: 2019 IEEE 21st International Conference on High Performance Computing and Communications; IEEE 17th International Conference on Smart City; IEEE 5th International Conference on Data Science and Systems (HPCC/SmartCity/DSS), pp 1249–1256. IEEE (2019). https://doi.org/10.1109/HPCC/SmartCity/DSS.2019.00175

  26. Chung, J., Gulcehre, C., Cho, K., & Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014) https://doi.org/10.48550/arXiv.1412.3555

  27. Bao, L., Yang, J., Zhang, Z., Liu, W., Chen, J., Wu, C.: On accurate prediction of cloud workloads with adaptive pattern mining. J. Supercomput. 1–28 (2022). https://doi.org/10.1007/s11227-022-04647-5

  28. Yazdanian, P., Sharifian, S.: E2LG: a multiscale ensemble of LSTM/GAN deep learning architecture for multistep-ahead cloud workload prediction. J. Supercomput. 1–31 (2021). https://doi.org/10.1007/s11227-021-03723-6

  29. 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) https://doi.org/10.1109/KST.2018.8426104

  30. Zhang, Z., Tang, X., Han, J., Wang, P.: Sibyl: Host load prediction with an efficient deep learning model in cloud computing. In: International Conference on Algorithms and Architectures for Parallel Processing, pp. 226–237. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-05054-2_17

  31. Bi, J., Li, S., Yuan, H., Zhou, M.: Integrated deep learning method for workload and resource prediction in cloud systems. Neurocomputing 424, 35–48 (2021). https://doi.org/10.1016/j.neucom.2020.11.011

    Article  Google Scholar 

  32. You, D., Lin, W., Shi, F., Li, J., Qi, D., Fong, S.: A novel approach for CPU load prediction of cloud server combining denoising and error correction. Computing 1–18 (2020). https://doi.org/10.1007/s00607-020-00865-y

  33. Xu, M., Song, C., Wu, H., Gill, S.S., Ye, K., Xu, C.: esDNN: deep neural network based multivariate workload prediction in cloud computing environments. ACM Trans. Internet Technol. (2022). https://doi.org/10.1145/3524114

    Article  Google Scholar 

  34. Karim, M.E., Maswood, M.M.S., Das, S., Alharbi, A.G.: BHyPreC: a novel Bi-LSTM based hybrid recurrent neural network model to predict the CPU workload of cloud virtual machine. IEEE Access 9, 131476–131495 (2021). https://doi.org/10.1109/ACCESS.2021.3113714

    Article  Google Scholar 

  35. Al-Asaly, M.S., Bencherif, M.A., Alsanad, A., Hassan, M.M.: A deep learning-based resource usage prediction model for resource provisioning in an autonomic cloud computing environment. Neural Comput. Appl. 34(13), 10211–10228 (2022). https://doi.org/10.1007/s00521-021-06665-5

    Article  Google Scholar 

  36. Ouhame, S., Hadi, Y., Ullah, A.: An efficient forecasting approach for resource utilization in cloud data center using CNN-LSTM model. Neural Comput. Appl. 33(16), 10043–10055 (2021). https://doi.org/10.1007/s00521-021-05770-9

    Article  Google Scholar 

  37. Gao, J., Wang, H., Shen, H.: Machine learning based workload prediction in cloud computing. In: 2020 29th International Conference on Computer Communications and Networks (ICCCN), pp. 1–9. IEEE (2020) https://doi.org/10.1109/ICCCN49398.2020.9209730

  38. Golshani, E., Ashtiani, M.: Proactive auto-scaling for cloud environments using temporal convolutional neural networks. J. Parallel Distrib. Comput. 154, 119–141 (2021). https://doi.org/10.1016/j.jpdc.2021.04.006

    Article  Google Scholar 

  39. Bai, S., Kolter, J. Z., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018). https://doi.org/10.48550/arXiv.1803.01271

  40. Singh, S., Chana, I.: QoS-aware autonomic resource management in cloud computing: a systematic review. ACM Comput. Surv. 48(3), 1–46 (2015). https://doi.org/10.1145/2843889

    Article  Google Scholar 

  41. Shen, W., Yin, B., Cao, X., Cheng, Y., Shen, X.: A distributed secure outsourcing scheme for solving linear algebraic equations in ad hoc clouds. IEEE Trans. Cloud Comput. 7(2), 415–430 (2017). https://doi.org/10.1109/TCC.2016.2647718

    Article  Google Scholar 

  42. Pippal, S. K., Mishra, S., Kushwaha, D. S.: Architectural design and issues for ad-hoc clouds. In International Conference on Advances in Communication, Network, and Computing, pp. 291–296. Springer, Berlin (2012). https://doi.org/10.1007/978-3-642-35615-5_44

  43. Oord, A. V. D., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., ...  Kavukcuoglu, K.: Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016). https://doi.org/10.48550/arXiv.1609.03499

  44. Yu, F., & Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015). https://doi.org/10.48550/arXiv.1511.07122

  45. Graves, A.: Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850 (2013). https://doi.org/10.48550/arXiv.1308.0850

  46. He, K., Zhang, X., Ren, S., Sun, J: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016). https://doi.org/10.1109/CVPR.2016.90

  47. Ba, J. L., Kiros, J. R., Hinton, G. E.: Layer normalization. arXiv preprint, arXiv:1607.06450 (2016) 

  48. Reiss, C., Wilkes, J., Hellerstein, J. L. Google cluster-usage traces: format+ schema. Google Inc., White Paper, 1 (2011)

  49. Google Cluster Trace 2011. https://github.com/google/cluster-data/blob/master/ClusterData2011_2.md

  50. Guo, J., Chang, Z., Wang, S., Ding, H., Feng, Y., Mao, L., Bao, Y.: Who limits the resource efficiency of my datacenter: An analysis of alibaba datacenter traces. In: 2019 IEEE/ACM 27th International Symposium on Quality of Service (IWQoS), pp. 1–10. IEEE (2019). https://doi.org/10.1145/3326285.3329074

  51. Alibaba Trace. clusterdata/trace_2018.md at master · alibaba/clusterdata · GitHub

  52. Auffarth, B.: Machine Learning for Time-Series with Python. Packt Publishing Ltd, Birmingham (2021)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, MNNIT Allahabad, Prayagraj, U.P., 211004, India

    Eva Patel & Dharmender Singh Kushwaha

Authors
  1. Eva Patel
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Dharmender Singh Kushwaha
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

The design and implementation of this study, analysis of the results, and preparation of the manuscript was carried out by all the authors.

Corresponding author

Correspondence to Eva Patel.

Ethics declarations

Ethics Approval and Consent to Participate

This work is the authors’ own original study and has not been previously published elsewhere.

Consent for Publication

All the authors consent to the publication of this study.

Competing Interests

The authors declare that they have no conflict of interest with regard to this manuscript.

Additional information

Publisher's Note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Patel, E., Kushwaha, D.S. An Integrated Deep Learning Prediction Approach for Efficient Modelling of Host Load Patterns in Cloud Computing. J Grid Computing 21, 5 (2023). https://doi.org/10.1007/s10723-022-09639-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10723-022-09639-6

Keywords

Search

Navigation