Empirical and analytical approaches for web server power modeling


Power-aware computing has emerged as a significant concern in data centers. In this work, we develop empirical models for estimating the power consumed by web servers. These models can be used by on-the-fly power-saving algorithms and are imperative for simulators that evaluate the power behavior of workloads. To apply power saving methodologies and algorithms at the data center level, we must first be able to measure or estimate the power and performance of individual servers running in the data centers. We show a novel method for developing full system web server power models that reduces non-linear relationships among performance measurements and system power and prunes model parameters. The web server power models use as parameters performance indicators read from the machine internal performance counters. We evaluate our approach on an AMD Opteron-based web server and on an Intel i7-based web sever. Our best model displays an average absolute error of 1.92 % for Intel i7 server and 1.46 % for AMD Opteron as compared to actual measurements, and 90th percentile for the absolute percent error equals to 2.66 % for Intel i7 and 2.08 % for AMD Opteron.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15


  1. 1.

    Reads/writes merged count the frequency that two 4 kB operations become one 8 kB operation


  1. 1.

    Standard performance evaluation corporation (SPEC). http://www.spec.org/web2009 (2009). Accessed 17 March 2009

  2. 2.

    Advanced Configuration and Power Interface Specification. http://www.acpi.info/spec.htm (2011). Accessed 29 November 2011

  3. 3.

    Barroso, L.A., Holzle, U.: The case for energy-proportional computing. IEEE Computer (2007)

  4. 4.

    Bellosa, F.: The benefits of event-driven energy accounting in power-sensitive Systems. In: EW 9: Proceedings of the 9th workshop on ACM SIGOPS European, workshop (2000)

  5. 5.

    Bergamaschi, R.A., Piga, L., Rigo, S., Azevedo, R., Araujo, G.: Data center power and performance optimization through global selection of p-states and utilization rates. Sustain Comput Inf Syst 2(4), 198–208 (2012)

    Google Scholar 

  6. 6.

    Bertran, R., Gonzalez, M., Martorell, X., Navarro, N., Ayguade, E.: Decomposable and responsive power models for multicore processors using performance counters. In ICS ’10: Proceedings of the 24th ACM International Conference on Supercomputing (2010)

  7. 7.

    Bohrer, P., Elnozahy, E. N., Keller, T., Kistler, M., Lefurgy, C., McDowell, C., Rajamony, R.: Power aware computing. The case for power management in web servers (2002)

  8. 8.

    Carrera, E. V., Pinheiro, E., Bianchini, R.: Conserving disk energy in network servers. In ICS ’03: Proceedings of the 17th annual international conference on Supercomputing (2003)

  9. 9.

    Chen, X., Xu, C., Dick, R.P., Mao, Z.M.: Performance and power modeling in a multi-programmed multi-core environment. In: Proceedings of the 47th Design Automation Conference (2010), DAC ’10.

  10. 10.

    Cochran, R., Hankendi, C., Coskun, A., Reda, S.: Pack & cap: adaptive dvfs and thread packing under power caps. In: 44th Annual IEEE/ACM International Symposium on Microarchitecture (2011)

  11. 11.

    Contreras, G., Martonosi, M.: Power prediction for Intel XScaleprocessors using performance monitoring unit events. In: ISLPED ’05: Proceedings of the 2005 international symposium on Low power electronics and design (2005)

  12. 12.

    Fan, X., Weber, W.-D., Barroso, L. A.: Power provisioning for a warehouse-sized computer. In: ISCA ’07: Proceedings of the 34th, annual international symposium on Computer architecture (2007)

  13. 13.

    Hall, M. A.: Correlation-based feature selection for machine learning. Ph.D. Thesis, University of Waikato (1999)

  14. 14.

    Instruments, N.: Bus-Powered M Series Multifunction DAQ for USB - 16-Bit, up to 400 kS/s, up to 32 Analog Inputs, Isolation Data Sheet (2009)

  15. 15.

    Intel.: Intel 64 and IA-32 Architectures Software Developer’s Manual Volume 3B: System Programming Guide, Part 2. Santa Clara, CA, USA (2013)

  16. 16.

    Isci, C., Buyuktosunoglu, A., Cher, C., Bose, P., Martonosi, M.: An analysis of efficient multicore global power management policies: Maximizing performance for a given power budget. In: 39th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO-39 2006) (2006)

  17. 17.

    Isci, C., Martonosi, M.: Runtime Power Monitoring in High-End Processors: Methodology and Empirical Data. In: MICRO 36: Proceedings of the 36th annual IEEE/ACM International Symposium on Microarchitecture (2003)

  18. 18.

    Joseph, R., Martonosi, M.: Run-time power estimation in high performance microprocessors. In: ISLPED ’01: Proceedings of the 2001 international symposium on Low power electronics and design (2001)

  19. 19.

    Ketchen, D.J., Shook, C.L.: The application of cluster analysis in strategic management research: an analysis and critique. Strateg Manag J 17(6), 441–458 (1996)

    Article  Google Scholar 

  20. 20.

    Laros, J., Pedretti, K., Kelly, S., Vandyke, J., Ferreira, K., Vaughan, C., Swan, M.: Topics on measuring real power usage on high performance computing platforms. In: CLUSTER ’09. IEEE International Conference on Cluster Computing and Workshops (2009)

  21. 21.

    LEM Components. Current transducer lts 25-NP data sheet (2008)

  22. 22.

    Lewis, A.W., Tzeng, N.-F., Ghosh, S.: Runtime energy consumption estimation for server workloads based on chaotic time-series approximation. ACM Trans. Archit. Code Optim. 9, 3 (Oct. 2012)

    Google Scholar 

  23. 23.

    Linux Kernel Organization. Block layer statistics: Linux Documentation Project (2010)

  24. 24.

    Lloyd, S.P.: Least squares quantization in PCM. IEEE Trans Inf Theor 28, 129–137 (1982)

    Article  MATH  MathSciNet  Google Scholar 

  25. 25.

    Lucer, C.D., Akella, C.: Power profiling for embedded applications. White paper (2009)

  26. 26.

    Piga, L., Bergamaschi, R., Azevedo, R., Rigo, S.: Power measuring infrastructure for computing systems. Institute of Computing, University of Campinas, Tech. rep. (2011)

    Google Scholar 

  27. 27.

    Rajamani, K., Rawson, F., Ware, M., Hanson, H., Carter, J., Rosedahl, T., Geissler, A., Silva, G., Hua, H.: Power-performance management on an IBM POWER7 server. In: ISLPED ’10: Proceedings of the 16th ACM/IEEE international symposium on Low power electronics and design (2010)

  28. 28.

    Red Hat Inc., Performance counters for linux (2010)

  29. 29.

    Rivoire, S., Ranganathan, P., Kozyrakis, C.A.: comparison of high-level full-system power models. In: HotPower’08 (2008)

  30. 30.

    Rivoire, S.M.: Models and metrics for energy-efficient computer systems. Ph.D. Thesis, Department of Electrical Engineering of Stanford University (2008)

  31. 31.

    Rotem, E., Naveh, A., Rajwan, D., Ananthakrishnan, A., Weissmann, E.: Power management architecture of the 2nd generation intel core microarchitecture, formerly codenamed sandy bridge. In: Hot Chips 23 (2011)

  32. 32.

    Zedlewski, J., Sobti, S., Garg, N., Zheng, F., Krishnamurthy, A., Wang, R.: Modeling hard-disk power consumption. In: FAST ’03: Proceedings of the 2nd USENIX Conference on File and Storage Technologies (2003)

Download references


We would like to thank the reviewers for their valuable suggestions. This work was partially supported by FAPESP Grant No. 2010/05389-5.

Author information



Corresponding author

Correspondence to Leonardo Piga.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Piga, L., Bergamaschi, R.A. & Rigo, S. Empirical and analytical approaches for web server power modeling. Cluster Comput 17, 1279–1293 (2014). https://doi.org/10.1007/s10586-014-0373-0

Download citation


  • Power Model
  • Absolute Percent Error
  • Context Switch
  • Disk Power
  • Miscellaneous Component