Abstract
With the development of cloud computing, energy consumption has become a major and costly problem in data centers. To improve the energy efficiency of data centers, we analyze the influence factors of energy consumption and discover that reducing the idle servers can effectively cut down the energy consumption of data centers. Then the load demand forecasting algorithm using weighted random forests is proposed. And time factor matching coefficient obtained by considering the day type and the time span is employed to calculate the weights. To enhance the forecasting performance, an error correction strategy is also introduced into the forecasting model. The experimental results show that these strategies further improve the prediction accuracy, and the root-mean-square error is 2.6–4.1% lower than other forecasting algorithms. We finally design an adaptive scheduling technology that utilizes short-term prediction of load demand. This technology adaptively adjusts the scale of the data center cluster based on the forecast results. The simulation results indicate that the technology can reduce 12.5% energy consumption while ensuring the service quality.
Similar content being viewed by others
References
Bankole AA, Ajila SA (2013) Predicting cloud resource provisioning using machine learning techniques. In: 2013 26th Annual IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), IEEE, pp 1–4
Batalla JM, Sienkiewicz K, Latoszek W, Krawiec P, Mavromoustakis CX, Mastorakis G (2016) Validation of virtualization platforms for i-iot purposes. J Supercomput 1–15
Beitelmal A, Fabris D (2014) Servers and data centers energy performance metrics. Energy Build 80:562–569
Boru D, Kliazovich D, Granelli F, Bouvry P, Zomaya AY (2015) Energy-efficient data replication in cloud computing datacenters. Clust Comput 18(1):385–402
Calheiros RN, Vecchiola C, Karunamoorthy D, Buyya R (2012) The aneka platform and QoS-driven resource provisioning for elastic applications on hybrid clouds. Future Gener Comput Syst 28(6):861–870
Chiang RCL, Hwang J, Huang HH, Wood T (2014) Matrix: achieving predictable virtual machine performance in the clouds. In: ICAC, pp 45–56
Dabbagh M, Hamdaoui B, Guizani M, Rayes A (2016) An energy-efficient VM prediction and migration framework for overcommitted clouds. IEEE Trans Cloud Comput PP(99):1–13. https://doi.org/10.1109/TCC.2016.2564403
Dayarathna M, Wen Y, Fan R (2016) Data center energy consumption modeling: a survey. IEEE Commun Surv Tutor 18(1):732–794
Di S, Kondo D, Cirne W (2012) 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. IEEE Computer Society Press, Washington, p 21
Duy TVT, Sato Y, Inoguchi Y (2010) Performance evaluation of a green scheduling algorithm for energy savings in cloud computing. In: 2010 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum (IPDPSW), IEEE, pp 1–8
Duy TVT, Sato Y, Inoguchi Y (2011) A prediction-based green scheduler for datacenters in clouds. IEICE Trans Inf Syst 94(9):1731–1741
Farahnakian F, Liljeberg P, Plosila J (2013) Lircup: linear regression based CPU usage prediction algorithm for live migration of virtual machines in data centers. In: 2013 39th EUROMICRO Conference on Software Engineering and Advanced Applications (SEAA), IEEE, pp 357–364
Farahnakian F, Pahikkala T, Liljeberg P, Plosila J, Hieu NT, Tenhunen H (2016) Energy-aware VM consolidation in cloud data centers using utilization prediction model. IEEE Trans Cloud Comput PP(99):1–13. https://doi.org/10.1109/TCC.2016.2617374
Islam S, Keung J, Lee K, Liu A (2012) Empirical prediction models for adaptive resource provisioning in the cloud. Future Gener Comput Syst 28(1):155–162
Javadi B, Abawajy J, Buyya R (2012) Failure-aware resource provisioning for hybrid cloud infrastructure. J Parallel Distrib Comput 72(10):1318–1331
Jheng JJ, Tseng FH, Chao HC, Chou LD (2014) A novel VM workload prediction using grey forecasting model in cloud data center. In: 2014 International Conference on Information Networking (ICOIN), IEEE, pp 40–45
Lai Z, Lam KT, Wang CL, Su J (2015) Latency-aware DVFS for efficient power state transitions on many-core architectures. J Supercomput 71(7):2720–2747
Lei H, Zhang T, Liu Y, Zha Y, Zhu X (2015) SGEESS: smart green energy-efficient scheduling strategy with dynamic electricity price for data center. J Syst Softw 108:23–38
Liang Q, Zhang J, Zhang Yh, Jm Liang (2014) The placement method of resources and applications based on request prediction in cloud data center. Inf Sci 279:735–745
Liao JS, Chang CC, Hsu YL, Zhang XW, Lai KC, Hsu CH (2012) Energy-efficient resource provisioning with SLA consideration on cloud computing. In: 2012 41st International Conference on Parallel Processing Workshops (ICPPW), IEEE, pp 206–211
Liu J, Zhao F, Liu X, He W (2009) Challenges towards elastic power management in internet data centers. In: 29th IEEE International Conference on Distributed Computing Systems Workshops, 2009. ICDCS Workshops’ 09. IEEE, pp 65–72
Luo L, Wu W, Zhang F (2014) Energy modeling based on cloud data center. J Softw 25(7):1371–1387
Meisner D, Gold BT, Wenisch TF (2011) The powernap server architecture. ACM Trans Comput Syst (TOCS) 29(1):3
Prevost JJ, Nagothu K, Kelley B, Jamshidi M (2011) Prediction of cloud data center networks loads using stochastic and neural models. In: 2011 6th International Conference on System of Systems Engineering (SoSE), IEEE, pp 276–281
Prevost JJ, Nagothu K, Jamshidi M, Kelley B (2015) Energy aware load prediction for cloud data centers. In: Control and Systems Engineering. Springer, New York, pp 153–174
Rittinghouse JW, Ransome JF (2016) Cloud computing: implementation, management, and security. CRC Press, Boca Raton
Simao J, Veiga L (2013) Flexible slas in the cloud with a partial utility-driven scheduling architecture. In: 2013 IEEE 5th International Conference on Cloud Computing Technology and Science (CloudCom). IEEE, vol 1, pp 274–281
Singh S, Chana I (2016) Resource provisioning and scheduling in clouds: Qos perspective. J Supercomput 72(3):926–960
Tseng FH, Wang X, Chou LD, Chao HC, Leung VCM (2017) Dynamic resource prediction and allocation for cloud data center using the multiobjective genetic algorithm. IEEE Syst J PP(99):1–12. https://doi.org/10.1109/JSYST.2017.2722476
Van Heddeghem W, Lambert S, Lannoo B, Colle D, Pickavet M, Demeester P (2014) Trends in worldwide ict electricity consumption from 2007 to 2012. Comput Commun 50:64–76
Xiong Z, Zeng S, Lu H (2014) Desdsim: a dynamic energy-saving deployment simulation platform for web server cluster. In: 2014 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), IEEE, pp 477–482
Xu X, Dou W, Zhang X, Chen J (2016) Enreal: an energy-aware resource allocation method for scientific workflow executions in cloud environment. IEEE Trans Cloud Comput 4(2):166–179
Yoon MS, Kamal AE, Zhu Z (2016) Requests prediction in cloud with a cyclic window learning algorithm. In: Globecom Workshops (GC Wkshps), 2016 IEEE. IEEE, pp 1–6
Yoon MS, Kamal AE, Zhu Z (2017) Adaptive data center activation with user request prediction. Comput Netw 122:191–204
Zhang Q, Zhani MF, Boutaba R, Hellerstein JL (2013) Harmony: dynamic heterogeneity-aware resource provisioning in the cloud. In: 2013 IEEE 33rd International Conference on Distributed Computing Systems (ICDCS). IEEE, pp 510–519
Zhang S, Zhao B, Wang F, Zhang D (2015) Short-term power load forecasting based on big data. Proc CSEE 1:37–42
Acknowledgements
This research project is supported by the National Natural Science Foundation of China (Grant No: 61303029).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Chen, M., Yuan, J., Liu, D. et al. An adaption scheduling based on dynamic weighted random forests for load demand forecasting. J Supercomput 76, 1735–1753 (2020). https://doi.org/10.1007/s11227-017-2223-3
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-017-2223-3