QoS and energy management with Petri nets: A self-adaptive framework

Energy use is becoming a key design consideration in computing infrastructures and services. In this paper we focus on service-based applications and we propose an adaptation framework that can be used to reduce power consumption according to the observed workload. The adaptation guarantees a trade-off between energy consumption and system performance. The approach is based on the principle of proportional energy consumption obtained by scaling down energy for unused resources, considering both the number of servers switched on and their operating frequencies. Stochastic Petri nets are proposed for the modeling of the framework concerns, their analyses give results about the trade-offs. The application of the approach to a simple case study shows its usefulness and practical applicability. Finally, different types of workloads are analyzed with validation purposes.

[1]  Rogério de Lemos,et al.  Software Engineering for Self-Adaptive Systems [outcome of a Dagstuhl Seminar] , 2009, Software Engineering for Self-Adaptive Systems.

[2]  Parthasarathy Ranganathan.  Recipe for efficiency: principles of power-aware computing , 2010, CACM.

[3]  Adam Wierman,et al.  Open Versus Closed: A Cautionary Tale , 2006, NSDI.

[4]  Ricardo Bianchini,et al.  Power and energy management for server systems , 2004, Computer.

[5]  Virgílio A. F. Almeida,et al.  Capacity Planning for Web Services: Metrics, Models, and Methods , 2001 .

[6]  Daniel Mossé,et al.  Power optimization for dynamic configuration in heterogeneous web server clusters , 2010, J. Syst. Softw..

[7]  Jon W. Mark,et al.  Parameter estimation for Markov modulated Poisson processes via the EM algorithm with time discretization , 1993, Telecommun. Syst..

[8]  Marco Ajmone Marsan,et al.  Modelling with Generalized Stochastic Petri Nets , 1995, PERV.

[9]  Tadashi Dohi,et al.  Faster Maximum Likelihood Estimation Algorithms for Markovian Arrival Processes , 2009, 2009 Sixth International Conference on the Quantitative Evaluation of Systems.

[10]  BeccutiMarco,et al.  The GreatSPN tool , 2009 .

[11]  Jeffrey O. Kephart,et al.  The Vision of Autonomic Computing , 2003, Computer.

[12]  Julie A. McCann,et al.  A survey of autonomic computing—degrees, models, and applications , 2008, CSUR.

[13]  Dirk Beyer,et al.  Self-Adaptive SLA-Driven Capacity Management for Internet Services , 2006, 2006 IEEE/IFIP Network Operations and Management Symposium NOMS 2006.

[14]  Evgenia Smirni,et al.  Dealing with Burstiness in Multi-Tier Applications: Models and Their Parameterization , 2012, IEEE Transactions on Software Engineering.

[15]  K. Meier-Hellstern.  A fitting algorithm for Markov-modulated poisson processes having two arrival rates , 1987 .

[16]  Evgenia Smirni,et al.  KPC-Toolbox: Best recipes for automatic trace fitting using Markovian Arrival Processes , 2010, Perform. Evaluation.

[17]  Wolfgang Fischer,et al.  The Markov-Modulated Poisson Process (MMPP) Cookbook , 1993, Perform. Evaluation.

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

[19]  Raffaela Mirandola,et al.  Enhancing a QoS-based self-adaptive framework with energy management capabilities , 2011, QoSA-ISARCS '11.

[20]  Axel Thümmler,et al.  Efficient phase-type fitting with aggregated traffic traces , 2007, Perform. Evaluation.

[21]  Calton Pu,et al.  Mistral: Dynamically Managing Power, Performance, and Adaptation Cost in Cloud Infrastructures , 2010, 2010 IEEE 30th International Conference on Distributed Computing Systems.

[22]  José Merseguer,et al.  ArgoSPE: Model-Based Software Performance Engineering , 2006, ICATPN.

[23]  Prashant J. Shenoy,et al.  Agile dynamic provisioning of multi-tier Internet applications , 2008, TAAS.

[24]  William H. Sanders,et al.  Using CPU gradients for performance-aware energy conservation in multitier systems , 2011, Sustain. Comput. Informatics Syst..

[25]  Jeff Magee,et al.  Self-Managed Systems: an Architectural Challenge , 2007, Future of Software Engineering (FOSE '07).

[26]  Peter Buchholz,et al.  An EM-Algorithm for MAP Fitting from Real Traffic Data , 2003, Computer Performance Evaluation / TOOLS.

[27]  Rajarshi Das,et al.  Autonomic multi-agent management of power and performance in data centers , 2008, AAMAS.

[28]  Miklós Telek,et al.  Markovian Modeling of Real Data Traffic: Heuristic Phase Type and MAP Fitting of Heavy Tailed and Fractal Like Samples , 2002, Performance.

[29]  Javier Campos,et al.  From UML activity diagrams to Stochastic Petri nets: application to software performance engineering , 2004, WOSP '04.

[30]  Ítalo S. Cunha,et al.  Analyzing security and energy tradeoffs in autonomic capacity management , 2008, NOMS 2008 - 2008 IEEE Network Operations and Management Symposium.

[31]  Simona Bernardi,et al.  Performance aware open-world software in a 3-layer architecture , 2010, WOSP/SIPEW '10.

[32]  Diego Perez-Palacin,et al.  Performance sensitive self-adaptive service-oriented software using hidden Markov models , 2011, ICPE '11.

[33]  T. Rydén.  An EM algorithm for estimation in Markov-modulated Poisson processes , 1996 .

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

[35]  H. Okamura,et al.  Markovian Arrival Process Parameter Estimation With Group Data , 2009, IEEE/ACM Transactions on Networking.

[36]  Jeffrey S. Chase,et al.  Balance of Power: Energy Management for Server Clusters , 2001 .

[37]  Anand Sivasubramaniam,et al.  Managing server energy and operational costs in hosting centers , 2005, SIGMETRICS '05.

[38]  Mary Shaw,et al.  Software Engineering for Self-Adaptive Systems: A Research Roadmap , 2009, Software Engineering for Self-Adaptive Systems.

[39]  Samuel Kounev,et al.  Model-based self-adaptive resource allocation in virtualized environments , 2011, SEAMS '11.

[40]  David E. Culler,et al.  USENIX Association Proceedings of USITS ’ 03 : 4 th USENIX Symposium on Internet Technologies and Systems , 2003 .