ABSTRACT
Modelling and analyzing power consumption for data centres can diagnose potential energy-hungry components and applications, and facilitate in-time control, benefiting the energy efficiency of data centers. However, solutions to this problem, including static power models and canonical prediction models, either aim to build a static relationship between power consumption and hardware/application configurations without considering the dynamic fluctuation of power; or simply treat it as time series, ignoring the inherit power data characteristics. To tackle these issues, in this paper, we present a systematic power prediction framework based on extensive power dynamic profiling and deep learning models. In particular, we first analyse different power series samples to illustrate their noise patterns; accordingly we propose a power data de-noising method, which lowers noise interference to the modelling. With the pretreated data, we propose two deep learning based prediction models, including a fine-grained model and a coarse-grained model, which are suitable for different time scales. In the fine-grained prediction model, a recursive autoencoder (AE) is employed for short-duration prediction; in the coarse-grained model, an AE is used to encode massive fine-grained historical data as a further data pretreatment for long-duration prediction. Experimental results show that our proposed models outperform canonical prediction methods with higher accuracy, up to 79% error reduction for certain cases.
- M. Arlitt and T. Jin. 1998 world cup web site access logs, 1998.Google Scholar
- M. F. Arlitt and C. L. Williamson. Web server workload characterization: The search for invariants. In ACM SIGMETRICS Performance Evaluation Review, volume 24, pages 126--137. ACM, 1996. Google ScholarDigital Library
- J. Choi, S. Govindan, B. Urgaonkar, and A. Sivasubramaniam. Profiling, prediction, and capping of power consumption in consolidated environments. In IEEE International Symposium on Modeling, Analysis and Simulation of Computers and Telecommunication Systems, pages 1--10. IEEE, 2008.Google ScholarCross Ref
- G. W. Corder and D. I. Foreman. Nonparametric statistics for non-statisticians: a step-by-step approach. John Wiley & Sons, 2009.Google ScholarCross Ref
- J. D. Davis, S. Rivoire, M. Goldszmidt, and E. K. Ardestani. Chaos: Composable highly accurate os-based power models. In IEEE International Symposium on Workload Characterization (IISWC), pages 153--163. IEEE, 2012. Google ScholarDigital Library
- E. M. Elnozahy, M. Kistler, and R. Rajamony. Energy-efficient server clusters. In Power-Aware Computer Systems, pages 179--197. Springer, 2003. Google ScholarDigital Library
- A. Gandhi, Y. Chen, D. Gmach, M. Arlitt, and M. Marwah. Minimizing data center sla violations and power consumption via hybrid resource provisioning. In 2011 International Green Computing Conference and Workshops (IGCC), pages 1--8. IEEE, 2011. Google ScholarDigital Library
- B. Heller, S. Seetharaman, P. Mahadevan, Y. Yiakoumis, P. Sharma, S. Banerjee, and N. McKeown. Elastictree: Saving energy in data center networks. In NSDI, volume 10, pages 249--264, 2010. Google ScholarDigital Library
- G. E. Hinton. Deep belief networks. Scholarpedia, 4(5): 5947, 2009.Google ScholarCross Ref
- G. E. Hinton and R. R. Salakhutdinov. Reducing the dimensionality of data with neural networks. Science, 313(5786): 504--507, 2006.Google ScholarCross Ref
- D. Kusic, J. O. Kephart, J. E. Hanson, N. Kandasamy, and G. Jiang. Power and performance management of virtualized computing environments via lookahead control. Cluster computing, 12(1): 1--15, 2009. Google ScholarDigital Library
- D. Meisner, B. T. Gold, and T. F. Wenisch. Powernap: eliminating server idle power. ACM SIGARCH Computer Architecture News, 37(1): 205--216, 2009. Google ScholarDigital Library
- X. Meng, V. Pappas, and L. Zhang. Improving the scalability of data center networks with traffic-aware virtual machine placement. In Proceedings IEEE INFOCOM, pages 1--9. IEEE, 2010. Google ScholarDigital Library
- S. Murugesan and G. Gangadharan. Harnessing green IT: Principles and practices. John Wiley & Sons, 2012. Google ScholarDigital Library
- R. Nathuji and K. Schwan. Virtualpower: coordinated power management in virtualized enterprise systems. In ACM SIGOPS Operating Systems Review, volume 41, pages 265--278. ACM, 2007. Google ScholarDigital Library
- E. Pinheiro, R. Bianchini, E. V. Carrera, and T. Heath. Load balancing and unbalancing for power and performance in cluster-based systems. In Workshop on compilers and operating systems for low power, volume 180, pages 182--195. Barcelona, Spain, 2001.Google Scholar
- E. N. Power. Energy logic: Reducing data center energy consumption by creating savings that cascade across systems. A White Paper from the Experts in Business-Critical Continuity, 2008.Google Scholar
- P. Ranganathan, P. Leech, D. Irwin, and J. Chase. Ensemble-level power management for dense blade servers. In ACM SIGARCH Computer Architecture News, volume 34, pages 66--77. IEEE Computer Society, 2006. Google ScholarDigital Library
- R. Sawyer. Calculating total power requirements for data centers. American Power Conversion, Tech. Rep, 70: 80--90, 2004.Google Scholar
- J. Schmidhuber. Deep learning in neural networks: An overview. arXiv preprint arXiv:1404.7828, 2014. Google ScholarDigital Library
- R. Socher, J. Pennington, E. H. Huang, A. Y. Ng, and C. D. Manning. Semi-supervised recursive autoencoders for predicting sentiment distributions. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 151--161. Association for Computational Linguistics, 2011. Google ScholarDigital Library
- Y. Song, H. Wang, Y. Li, B. Feng, and Y. Sun. Multi-tiered on-demand resource scheduling for vm-based data center. In Proceedings of the 2009 9th IEEE/ACM International Symposium on Cluster Computing and the Grid, pages 148--155. IEEE Computer Society, 2009. Google ScholarDigital Library
- G. Tesauro, R. Das, H. Chan, J. Kephart, D. Levine, F. Rawson, and C. Lefurgy. Managing power consumption and performance of computing systems using reinforcement learning. In Advances in Neural Information Processing Systems, pages 1497--1504, 2007.Google Scholar
- G. Tesauro, N. K. Jong, R. Das, and M. N. Bennani. A hybrid reinforcement learning approach to autonomic resource allocation. In IEEE International Conference on Autonomic Computing (ICAC), pages 65--73. IEEE, 2006. Google ScholarDigital Library
- G. Von Laszewski, L. Wang, A. J. Younge, and X. He. Power-aware scheduling of virtual machines in dvfs-enabled clusters. In Cluster Computing and Workshops, 2009. CLUSTER'09. IEEE International Conference on, pages 1--10. IEEE, 2009.Google ScholarCross Ref
- D. Wang, C. Ren, S. Govindan, A. Sivasubramaniam, B. Urgaonkar, A. Kansal, and K. Vaid. Ace: Abstracting, characterizing and exploiting datacenter power demands. In IEEE International Symposium on Workload Characterization (IISWC), pages 44--55. IEEE, 2013.Google ScholarCross Ref
- J. Yin, P. Sun, Y. Wen, H. Gong, M. Liu, X. Li, H. You, J. Gao, and C. Lin. Cloud3dview: an interactive tool for cloud data center operations. In Proceedings of the ACM SIGCOMM 2013 conference on SIGCOMM, pages 499--500. ACM, 2013. Google ScholarDigital Library
- F. Zanini, D. Atienza, L. Benini, and G. De Micheli. Multicore thermal management with model predictive control. In European Conference on Circuit Theory and Design (ECCTD), pages 711--714. IEEE, 2009.Google ScholarCross Ref
- Q. Zhu, F. M. David, C. F. Devaraj, Z. Li, Y. Zhou, and P. Cao. Reducing energy consumption of disk storage using power-aware cache management. In IEE Proceedings-Software, pages 118--118. IEEE, 2004. Google ScholarDigital Library
Index Terms
- Learning-based power prediction for data centre operations via deep neural networks
Recommendations
A methodology to predict the power consumption of servers in data centres
e-Energy '11: Proceedings of the 2nd International Conference on Energy-Efficient Computing and NetworkingUntil recently, there have been relatively few studies exploring the power consumption of ICT resources in data centres. In this paper, we propose a methodology to capture the behaviour of most relevant energy-related ICT resources in data centres and ...
Specification of Data Centre Power Management Strategies
e-Energy '17: Proceedings of the Eighth International Conference on Future Energy SystemsIn recent work, we proposed a flexible simulation framework (using AnyLogic) for the trade-off analysis of power and performance in data centres. We now extend this framework with a versatile module to study the effect of advanced power management ...
Mapping Data Centre Business Types with Power Management Strategies to Identify Demand Response Candidates
e-Energy '18: Proceedings of the Ninth International Conference on Future Energy SystemsData centres are key to a future energy system with a high share of intermittent renewable energy sources. They form the cloud that enables a modern life-style and cyber-physical based production; however, fulfilling these tasks makes them the fastest ...
Comments