Learning-based power prediction for data centre operations via deep neural networks

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.

[1]  Amir F. Atiya,et al.  Multi-step-ahead prediction using dynamic recurrent neural networks , 2000, Neural Networks.

[2]  Xuelong Li,et al.  Cloud3DView: an interactive tool for cloud data center operations , 2013, SIGCOMM.

[3]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[4]  Kushagra Vaid,et al.  ACE: Abstracting, characterizing and exploiting datacenter power demands , 2013, 2013 IEEE International Symposium on Workload Characterization (IISWC).

[5]  I. J. Leontaritis,et al.  Input-output parametric models for non-linear systems Part II: stochastic non-linear systems , 1985 .

[6]  David E. Irwin,et al.  Ensemble-level Power Management for Dense Blade Servers , 2006, 33rd International Symposium on Computer Architecture (ISCA'06).

[7]  Kushagra Vaid,et al.  ACE: abstracting, characterizing and exploiting peaks and valleys in datacenter power consumption , 2013, SIGMETRICS '13.

[8]  Giovanni De Micheli,et al.  Multicore thermal management with model predictive control , 2009, 2009 European Conference on Circuit Theory and Design.

[9]  San Murugesan,et al.  Harnessing Green IT: Principles and Practices , 2008, IT Professional.

[10]  Karsten Schwan,et al.  VirtualPower: coordinated power management in virtualized enterprise systems , 2007, SOSP.

[11]  이상헌,et al.  Deep Belief Networks , 2010, Encyclopedia of Machine Learning.

[12]  Manish Marwah,et al.  Minimizing data center SLA violations and power consumption via hybrid resource provisioning , 2011, 2011 International Green Computing Conference and Workshops.

[13]  Vasileios Pappas,et al.  Improving the Scalability of Data Center Networks with Traffic-aware Virtual Machine Placement , 2010, 2010 Proceedings IEEE INFOCOM.

[14]  Xi He,et al.  Power-aware scheduling of virtual machines in DVFS-enabled clusters , 2009, 2009 IEEE International Conference on Cluster Computing and Workshops.

[15]  David Levine,et al.  Managing Power Consumption and Performance of Computing Systems Using Reinforcement Learning , 2007, NIPS.

[16]  Sujata Banerjee,et al.  ElasticTree: Saving Energy in Data Center Networks , 2010, NSDI.

[17]  Hui Wang,et al.  Multi-Tiered On-Demand Resource Scheduling for VM-Based Data Center , 2009, 2009 9th IEEE/ACM International Symposium on Cluster Computing and the Grid.

[18]  Rajarshi Das,et al.  A Hybrid Reinforcement Learning Approach to Autonomic Resource Allocation , 2006, 2006 IEEE International Conference on Autonomic Computing.

[19]  Jeffrey Pennington,et al.  Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions , 2011, EMNLP.

[20]  Martin F. Arlitt,et al.  Web server workload characterization: the search for invariants , 1996, SIGMETRICS '96.

[21]  Anand Sivasubramaniam,et al.  Profiling, Prediction, and Capping of Power Consumption in Consolidated Environments , 2008, 2008 IEEE International Symposium on Modeling, Analysis and Simulation of Computers and Telecommunication Systems.

[22]  Yuanyuan Zhou,et al.  Reducing Energy Consumption of Disk Storage Using Power-Aware Cache Management , 2004, 10th International Symposium on High Performance Computer Architecture (HPCA'04).

[23]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[24]  Enrique V. Carrera,et al.  Load balancing and unbalancing for power and performance in cluster-based systems , 2001 .

[25]  S. Havlin,et al.  Detecting long-range correlations with detrended fluctuation analysis , 2001, cond-mat/0102214.

[26]  Nagarajan Kandasamy,et al.  Power and performance management of virtualized computing environments via lookahead control , 2008, 2008 International Conference on Autonomic Computing.

[27]  John D. Davis,et al.  CHAOS: Composable Highly Accurate OS-based power models , 2012, 2012 IEEE International Symposium on Workload Characterization (IISWC).

[28]  Thomas F. Wenisch,et al.  PowerNap: eliminating server idle power , 2009, ASPLOS.

[29]  Gregory W. Corder,et al.  Nonparametric Statistics for Non-Statisticians: A Step-by-Step Approach , 2009 .

[30]  E. N. Elnozahy,et al.  Energy-Efficient Server Clusters , 2002, PACS.