PRACTISE: Robust prediction of data center time series

We analyze workload traces from production data centers and focus on their VM usage patterns of CPU, memory, disk, and network bandwidth. Burstiness is a clear characteristic of many of these time series: there exist peak loads within clear periodic patterns but also within patterns that do not have clear periodicity. We present PRACTISE, a neural network based framework that can efficiently and accurately predict future loads, peak loads, and their timing. Extensive experimentation using traces from IBM data centers illustrates PRACTISE's superiority when compared to ARIMA and baseline neural network models, with average prediction errors that are significantly smaller. Its robustness is also illustrated with respect to the prediction window that can be short-term (i.e., hours) or long-term (i.e., a week).

[1]  R. Larsen,et al.  An introduction to mathematical statistics and its applications (2nd edition) , by R. J. Larsen and M. L. Marx. Pp 630. £17·95. 1987. ISBN 13-487166-9 (Prentice-Hall) , 1987, The Mathematical Gazette.

[2]  Y.-Y. Hsu,et al.  Short term load forecasting using a multilayer neural network with an adaptive learning algorithm , 1992 .

[3]  James D. Hamilton.  Time Series Analysis , 1994 .

[4]  M.H. Hassoun,et al.  Fundamentals of Artificial Neural Networks , 1996, Proceedings of the IEEE.

[5]  William Remus,et al.  Neural Network Models for Time Series Forecasts , 1996 .

[6]  Neil Davey,et al.  Time Series Prediction and Neural Networks , 2001, J. Intell. Robotic Syst..

[7]  Amin Vahdat,et al.  Managing energy and server resources in hosting centers , 2001, SOSP.

[8]  Daniel A. Reed,et al.  Learning to Classify Parallel Input/Output Access Patterns , 2002, IEEE Trans. Parallel Distributed Syst..

[9]  M. K. Soni,et al.  Artificial Neural Network-Based Peak Load Forecasting Using Conjugate Gradient Methods , 2002, IEEE Power Engineering Review.

[10]  Graham J. G. Upton,et al.  A Dictionary of Statistics , 2002 .

[11]  A. ADoefaa,et al.  ? ? ? ? f ? ? ? ? ? , 2003 .

[12]  Daniel A. Reed,et al.  Automatic ARIMA time series modeling for adaptive I/O prefetching , 2004, IEEE Transactions on Parallel and Distributed Systems.

[13]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[14]  Andrew Warfield,et al.  Live migration of virtual machines , 2005, NSDI.

[15]  Arun Venkataramani,et al.  Black-box and Gray-box Strategies for Virtual Machine Migration , 2007, NSDI.

[16]  Raymond R. Hill,et al.  Discrete-Event Simulation: A First Course , 2007, J. Simulation.

[17]  A. Moore,et al.  Forecasting Web Page Views: Methods and Observations , 2008 .

[18]  Xiaoyun Zhu,et al.  1000 Islands: Integrated Capacity and Workload Management for the Next Generation Data Center , 2008, 2008 International Conference on Autonomic Computing.

[19]  Deepak Ganesan,et al.  PRESTO: feedback-driven data management in sensor networks , 2009, TNET.

[20]  Joseph M. Hellerstein,et al.  MAD Skills: New Analysis Practices for Big Data , 2009, Proc. VLDB Endow..

[21]  Paul Goodwin,et al.  The Holt-Winters Approach to Exponential Smoothing: 50 Years Old and Going Strong , 2010 .

[22]  Luís E. T. Rodrigues,et al.  A Machine Learning Approach to Performance Prediction of Total Order Broadcast Protocols , 2010, 2010 Fourth IEEE International Conference on Self-Adaptive and Self-Organizing Systems.

[23]  Amir F. Atiya,et al.  An Empirical Comparison of Machine Learning Models for Time Series Forecasting , 2010 .

[24]  S. Shankar Sastry,et al.  Revisit Dynamic ARIMA Based Anomaly Detection , 2011, 2011 IEEE Third Int'l Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third Int'l Conference on Social Computing.

[25]  Robert S. Leiken,et al.  A User’s Guide , 2011 .

[26]  Liang Dong,et al.  Starfish: A Self-tuning System for Big Data Analytics , 2011, CIDR.

[27]  Sven F. Crone,et al.  Advances in forecasting with neural networks? Empirical evidence from the NN3 competition on time series prediction , 2011 .

[28]  Arif Merchant,et al.  Projecting disk usage based on historical trends in a cloud environment , 2012, ScienceCloud '12.

[29]  Pedro Sousa,et al.  Multi‐scale Internet traffic forecasting using neural networks and time series methods , 2010, Expert Syst. J. Knowl. Eng..

[30]  Evgenia Smirni,et al.  State-of-the-practice in data center virtualization: Toward a better understanding of VM usage , 2013, 2013 43rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN).

[31]  Calton Pu,et al.  vPerfGuard: an automated model-driven framework for application performance diagnosis in consolidated cloud environments , 2013, ICPE '13.

[32]  S. Cadrin,et al.  Estimating Effective Sample Size for Monitoring Length Distributions: A Comparative Study of Georges Bank Groundfish , 2013 .

[33]  Andrea C. Arpaci-Dusseau,et al.  Warming up storage-level caches with bonfire , 2013, FAST.

[34]  Alma Riska,et al.  Storage Workload Isolation via Tier Warming: How Models Can Help , 2014, ICAC.

[35]  Evgenia Smirni,et al.  (Big)data in a virtualized world: volume, velocity, and variety in cloud datacenters , 2014, FAST.

[36]  Bowen Zhou,et al.  Mitigating interference in cloud services by middleware reconfiguration , 2014, Middleware.

[37]  Yellu Sreenivasulu,et al.  FAST TRANSPARENT MIGRATION FOR VIRTUAL MACHINES , 2014 .

[38]  Zhenyun Zhuang,et al.  Capacity Planning and Headroom Analysis for Taming Database Replication Latency: Experiences with LinkedIn Internet Traffic , 2015, ICPE.

[39]  Mark Beale,et al.  Neural Network Toolbox™ User's Guide , 2015 .