Abstract
Machine learning algorithms play an important role in resource management, allowing the improvement of the efficiency of resource usage in data centers (DCs) by predicting workload trends. In this paper, we propose a simplified system to predict the CPU usage of virtual machines (VMs) in a DC using Linear Regression Models while performing VM clustering based on common statistical characteristics of VM time series, which facilitates grouping VMs with similar behaviors and establishing clusters based on these characteristics. For each cluster, three representative VMs are established based on the time series of the closest VM to the cluster centroid, averaged time series for the cluster, and concatenated time series. Then, training of representative VMs is performed to finally choose the one with the lowest mean error per cluster. Simulation results show that, by performing clustering and training the model with representative time series, it is indeed possible to obtain a low mean error while reducing the local training time per VM.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aceto, G., Botta, A., de Donato, W., Pescapè, A.: Cloud monitoring: a survey. Comput. Netw. 57(9), 2093–2115 (2013). https://doi.org/10.1016/j.comnet.2013.04.001
Amazon: Time series forecasting principles with amazon forecast (2021)
Borkowski, M., Schulte, S., Hochreiner, C.: Predicting cloud resource utilization. In: IEEE/ACM 9th International Conference on Utility and Cloud Computing (UCC), pp. 37–42 (2016)
Box, G.E., Jenkins, G.M., Reinsel, G.C., Ljung, G.M.: Time Series Analysis: Forecasting and Control. John Wiley & Sons (2015)
Dai, L., Li, J.H.: An optimal resource allocation algorithm in cloud computing environment. Appl. Mech. Mater. 733, 779–783 (2015)
Daraghmeh, M., Agarwal, A., Manzano, R., Zaman, M.: Time series forecasting using facebook prophet for cloud resource management. In: IEEE International Conference on Communications Workshops (ICC Workshops), pp. 1–6 (2021)
Estrada, R., Asanza, V., Torres, D., Bazurto, A., Valeriano, I.: Learning-based energy consumption prediction. Procedia Comput. Sci. 203, 272–279 (2022)
Farahnakian, F., Liljeberg, P., Plosila, J.: LiRCUP: Linear regression based CPU usage prediction algorithm for live migration of virtual machines in data centers. In: Proceedings - 39th Euromicro Conference Series on Software Engineering and Advanced Applications, SEAA 2013, pp. 357–364 (2013)
Gill, P., Jain, N., Nagappan, N.: Understanding network failures in data centers: measurement, analysis, and implications. SIGCOMM Comput. Commun. Rev. 41(4), 350–361 (2011)
Gupta, S., Dinesh, D.A.: Resource usage prediction of cloud workloads using deep bidirectional long short term memory networks. In: IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS), pp. 1–6 (2017)
Hindman, B., et al.: Mesos: a platform for fine-grained resource sharing in the data center. In: NSDI’11, pp. 295–308. USENIX Association, USA (2011)
Iqbal, W., Erradi, A., Mahmood, A.: Dynamic workload patterns prediction for proactive autoscaling of web applications. J. Netw. Comput. Appl. 124, 94–107 (2018)
Janardhanan, D., Barrett, E.: Cpu workload forecasting of machines in data centers using lstm recurrent neural networks and arima models. In: 12th International Conference for Internet Technology and Secured Transactions (ICITST), pp. 55–60 (2017)
Kumar, J., Goomer, R., Singh, A.K.: Long short term memory recurrent neural network (LSTM-RNN) based workload forecasting model for cloud datacenters. Procedia Comput. Sci. 125, 676–682 (2018)
Kumar, J., Singh, A.K.: Cloud datacenter workload estimation using error preventive time series forecasting models. Clust. Comput. 23(2), 1363–1379 (2019). https://doi.org/10.1007/s10586-019-03003-2
Lindemann, B., Muller, T., Vietz, H., Jazdi, N., Weyrich, M.: A survey on long short-term memory networks for time series prediction. Procedia CIRP 99, 650–655 (2021)
Mormul, M., Hirmer, P., Stach, C., Mitschang, B.: Dear: distributed evaluation of alerting rules. In: IEEE 13th International Conference on Cloud Computing (CLOUD), pp. 158–165 (2020)
Nashold, L., Krishnan, R.: Using lstm and sarima models to forecast cluster cpu usage. ArXiv abs/2007.08092 (2020)
Qiu, F., Zhang, B., Guo, J.: A deep learning approach for vm workload prediction in the cloud. In: 17th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), pp. 319–324 (2016)
Rao, S.N., Shobha, G., Prabhu, S., Deepamala, N.: Time Series Forecasting methods suitable for prediction of CPU usage. In: 4th International Conference on Computational Systems and Information Technology for Sustainable Solution (CSITSS), vol. 4, pp. 1–5 (2019)
Sarikaa, S., Niranjana, S., Sri, K.V.D.: Time series forecasting of cloud resource usage. In: 6th International Conference on Computing, Communication and Automation (ICCCA), pp. 372–382 (2021)
TUDelft, D.U.o.T.: Dataset gwa-t-12-bitbrains. http://gwa.ewi.tudelft.nl/datasets/gwa-t-12-bitbrainss (2023)
U-chupala, P., Watashiba, Y., Ichikawa, K., Date, S., Iida, H.: Container rebalancing: Towards proactive linux containers placement optimization in a data center. In: IEEE 41st Annual Computer Software and Applications Conference (COMPSAC) 01, pp. 788–795 (2017)
Wang, J., Yan, Y., Guo, J.: Research on the prediction model of cpu utilization based on arimabp neural network (2016)
Xue, J., Yan, F., Birke, R., Chen, L.Y., Scherer, T., Smirni, E.: PRACTISE: robust prediction of data center time series. In: 11th International Conference on Network and Service Management (CNSM), pp. 126–134. IEEE (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Estrada, R., Valeriano, I., Aizaga, X. (2023). CPU Usage Prediction Model: A Simplified VM Clustering Approach. In: Barolli, L. (eds) Complex, Intelligent and Software Intensive Systems. CISIS 2023. Lecture Notes on Data Engineering and Communications Technologies, vol 176. Springer, Cham. https://doi.org/10.1007/978-3-031-35734-3_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-35734-3_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35733-6
Online ISBN: 978-3-031-35734-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)