Abstract
Cloud computing leverages virtualization as the most popular technique to deploy enterprise applications on virtual machines. Since the cloud system dynamically adapts to workload changes depending on the time of the day. It is required to ensure elasticity as a robust technique to efficiently model the changing workload requirements. However, it is an extremely challenging task, as several users may enter and depart from the cloud system over time. Predicting the different resource usage metrics of dynamically arriving jobs can help the cloud service providers (CSPs) in better capacity planning to fulfill the service level agreements (SLAs). In this paper, we propose a k clustering-based stacked bidirectional LSTM (BiLSTM) deep learners to model the multi-variate resource usage predictions for highly varying cloud workloads. We evaluate the proposed model on the Google cluster trace and validate its performance with the current approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhang, Q., Cheng, L., Boutaba, R.: Cloud computing: state-of-the-art and research challenges. Internet Serv. Appl. 1(1), 7–18 (2010)
Kaur, T., Chana, I.: Energy efficiency techniques in cloud computing: a survey and taxonomy. ACM Comput. Surv. 48(2), 22:1-22:46 (2015)
Zhang, Q., et al.: Dynamic energy-aware capacity provisioning for cloud computing environments. In: International Conference on Autonomic Computing (ICAC), pp. 145–154. ACM, New York (2012)
Caglar, F., Gokhale, A.: iOverbook: intelligent resource overbooking to support soft real-time applications in the cloud. In: IEEE 7th International Conference on Cloud Computing (CLOUD), pp. 538–545. IEEE, Anchorage (2014)
Gong, Z., Gu, X., Wilkes, J.: PRESS: PRedictive elastic ReSource scaling for cloud systems. In: International Conference on Network and Service Management (CNSM), pp. 9–16. IEEE, Niagara Falls (2010)
Nguyen, H., Shen, Z., Gu, X., Subbiah, S., Wilkes, J.: AGILE: elastic distributed resource scaling for infrastructure-as-a-service. In: 10th International Conference on Autonomic Computing (ICAC), pp. 69–82. USENIX, San Jose (2013)
Ghorbani, M., Wang, Y., Xue, Y., Pedram, M., Bogdan, P.: Prediction and control of bursty cloud workloads: a fractal framework. In: International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS), pp. 1–9 (2014)
Reiss, C., Wilkes, J., Hellerstein, J.L.: Google cluster-usage traces: format + schema, November 2011
Song, B., Yu, Y., Zhou, Y., et al.: Host load prediction with long short-term memory in cloud computing. J. Supercomput. 74, 6554–6568 (2018)
Aboagye-Sarfo, P., et al.: A comparison of multivariate and univariate time series approaches to modelling and forecasting emergency department demand in Western Australia. J. Biomed. Inform. 57, 62–73 (2015)
Gupta, S., Dinesh, D.A.: Resource usage prediction of cloud workloads using deep bidirectional long short term memory networks. In: International Conference on Advanced Networks and Telecommunications Systems (ANTS), pp. 1–6. IEEE, Bhubaneswar (2017)
Wakuya, H., Shida, K.: Bi-directionalization of neural computing architecture for time series prediction. III. Application to laser intensity time record Data Set A. In: International Joint Conference on Neural Networks (IJCNN), pp. 2098–2103. IEEE, Washington (2001)
Zhao, Y., Ye, L., Li, Z., Song, X., Lang, Y., Su, J.: A novel bidirectional mechanism based on time series model for wind power forecasting. Appl. Energy 177, 793–803 (2016)
Acknowledgements
The work is partially supported by Department of Science and Technology (DST), Government of India under ICPS Programme through the Project No.: DST/ICPS/CPS-Individual/2018/403(G), “Low-cost Energy-Efficient Cloud for Cyber-Physical Disaster Management Systems”. The first author, Yashwant Singh Patel, acknowledges Visvesvaraya Ph.D. Scheme for Electronics and IT under Ministry of Electronics and Information Technology (MeitY), Government of India for supporting this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Patel, Y.S., Jaiswal, R., Pandey, S., Misra, R. (2021). k Stacked Bidirectional LSTM for Resource Usage Prediction in Cloud Data Centers. In: Misra, R., Kesswani, N., Rajarajan, M., Bharadwaj, V., Patel, A. (eds) Internet of Things and Connected Technologies. ICIoTCT 2020. Advances in Intelligent Systems and Computing, vol 1382. Springer, Cham. https://doi.org/10.1007/978-3-030-76736-5_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-76736-5_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-76735-8
Online ISBN: 978-3-030-76736-5
eBook Packages: EngineeringEngineering (R0)