Advertisement

SOC Dynamic Power Management Using Artificial Neural Network

  • Huaxiang Lu
  • Yan Lu
  • Zhifang Tang
  • Shoujue Wang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4221)

Abstract

Dynamic Power Management (DPM) is a technique to reduce power consumption of electronic system by selectively shutting down idle components. In this article we try to introduce back propagation network and radial basis network into the research of the system-level power management policies. We proposed two PM policies-Back propagation Power Management (BPPM) and Radial Basis Function Power Management (RBFPM) which are based on Artificial Neural Networks (ANN). Our experiments show that the two power management policies greatly lowered the system-level power consumption and have higher performance than traditional Power Management(PM) techniques — BPPM is 1.09-competitive and RBFPM is 1.08-competitive vs. 1.79, 1.45, 1.18-competitive separately for traditional timeout PM, adaptive predictive PM and stochastic PM.

Keywords

Artificial Neural Network Idle Time Power Management Idle Period Back Propagation Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Yardi, S., Channakeshava, K., Hsiao, M.S., Martin, T.L., Ha, D.S.: A formal framework for modeling and analysis of system-level dynamic power management. In: Proceedings International Conference, Computer Design, 2005, October 2-5, pp. 119–126 (2005)Google Scholar
  2. 2.
    Ren, Z., Krogh, B.H., Marculescu, R.: Hierarchical adaptive dynamic power management. Computers, IEEE Transactions 54(4), 409–420 (2005)CrossRefGoogle Scholar
  3. 3.
    Mihic, K., Simunic, T., De Micheli, G.: Reliability and power management of integrated systems. In: Euromicro Symposium on Digital System Design, DSD 2004, August 31-September 3, pp. 5–11 (2004)Google Scholar
  4. 4.
    Lu, Y.-H., De Micheli, G.: Comparing system level power management policies. Design & Test of Computers 18(2), 10–19 (2001)CrossRefGoogle Scholar
  5. 5.
    Ramanathan, D., Irani, S., Gupta, R.K.: An analysis of system level power management algorithms and their effects on latency. IEEE Trans. Computer-Aided Design 21(3) (March 2002)Google Scholar
  6. 6.
    Zheng, R., Hou, J.C., Sha, L.: On time-out driven power management policies in wireless networks. In: Global Telecommunications Conference, GLOBECOM 2004, November 29-December 3, vol. 6, pp. 4097–4103. IEEE, Los Alamitos (2004)Google Scholar
  7. 7.
    Srivastava, M., Chandrakasan, A., Brodersen, R.: Predictive system shutdown and other architectural techniques for energy efficient programmable computation. IEEE Transactions on VUL Systems 4(1), 42–55 (1996)CrossRefGoogle Scholar
  8. 8.
    Hwang, C.-H., Wu, A.: A predictive system shutdown method for energy saving of event-Driven computation. In: Proceedings of the Int.1 Conference on Computer Aided Design, pp. 28–32 (1997)Google Scholar
  9. 9.
    Norman, G., Parker, D., Kwiatkowska, M., Shukla, S.K., Gupta, R.K.: Formal analysis and validation of continuous-time Markov chain based system level power management strategies. In: Seventh IEEE International High-Level Design Validation and Test Workshop, October 27-29, 2002, pp. 45–50 (2002)Google Scholar
  10. 10.
    Qu, Q., Pedram, M.: Stochastic modeling of a power-managed system-construction and optimization. IEEE Transactions Computer-Aided Design of Integrated Circuits and Systems 20(10), 1200–1217 (2001)CrossRefGoogle Scholar
  11. 11.
    Irani, S., Shukla, S., Gupta, R.: Competitive analysis of dynamic power management strategies for systems with multiple power saving states. In: Proceedings Design, Automation and Test in Europe Conference and Exhibition, March 4-8, 2002, pp. 117–123 (2002)Google Scholar
  12. 12.
    Huang, G.-B., Saratchandran, P., Sundararajan, N.: A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation. IEEE Transactions Neural Networks 16(1), 57–67 (2005)CrossRefGoogle Scholar
  13. 13.
    Shoujue, W., Jingpu, S., Chuan, C., Yujian, L.: Direction-basis-function neural networks. In: International Joint Conference Neural Networks, July 10-16, 1999, vol. 2, pp. 1251–1254 (1999)Google Scholar
  14. 14.
    Shoujue, W., et al.: Priority ordered neural networks with better similarity to human knowledge representation. Chinese Journal of Electronics 8(1), 1–4 (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Huaxiang Lu
    • 1
  • Yan Lu
    • 1
  • Zhifang Tang
    • 1
  • Shoujue Wang
    • 1
  1. 1.Neural Network LaboratoryInstitute of Semiconductors, Chinese Academy of SciencesBeijingChina

Personalised recommendations