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.
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
Goodfellow, I., Bengio, Y., Courville, A.: Deep learning. MIT press (2016)
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.
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
Graves, A.: Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850 (2013). https://doi.org/10.48550/arXiv.1308.0850
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
Ba, J. L., Kiros, J. R., Hinton, G. E.: Layer normalization. arXiv preprint, arXiv:1607.06450 (2016)
Reiss, C., Wilkes, J., Hellerstein, J. L. Google cluster-usage traces: format+ schema. Google Inc., White Paper, 1 (2011)
Google Cluster Trace 2011. https://github.com/google/cluster-data/blob/master/ClusterData2011_2.md
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
Alibaba Trace. clusterdata/trace_2018.md at master · alibaba/clusterdata · GitHub
Auffarth, B.: Machine Learning for Time-Series with Python. Packt Publishing Ltd, Birmingham (2021)
Author information
Authors and Affiliations
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
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.
About this article
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
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10723-022-09639-6