Online learning based on a novel cost function for system power management

Online learning based on a novel cost function for system power management

For access to this article, please select a purchase option:

Buy article PDF
(plus tax if applicable)
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Your details
Why are you recommending this title?
Select reason:
IET Computers & Digital Techniques — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

A novel system power management technique is proposed that employs a novel cost function based on state-action. Compared with the conventional algorithm, by using multiple parameter constraints in cost function of power management framework, the improved Q-learning can effectively make decisions to achieve a rational optimisation room. The proposed power management framework does not need any prior data and is running on a power model. As uncertainties can be effectively captured and modelled, the framework based on the model can help to explore an ideal trade-off and converge to the best power management policy. The results obtained showed that improved algorithm achieved remarkable significance.


    1. 1)
      • 1. Langen, P., Juurlink, B.: ‘Leakage-aware multiprocessor scheduling for low power’, J. Signal Process. Syst., 2006, 57, pp. 7380.
    2. 2)
      • 2. Tsai, Y.F., Vijaykrishnan, N., Xie, Y., et al: ‘Influence of leakage reduction techniques on delay/leakage uncertainty’. IEEE Conf. on VLSI Design, Kolkata, India, 2005, pp. 374379.
    3. 3)
      • 3. Basu, A., Lin, S.C., Wason, V., et al: ‘Simultaneous optimization of supply and threshold voltages for low-power and high-performance circuits in the leakage dominate era’. ACM Conf. on Design Automation, San Diego, USA, 2004, vol. 43, pp. 884887.
    4. 4)
      • 4. Jejurikar, R., Pereira, C., Gupta, R.: ‘Leakage aware dynamic voltage scaling for real-time embedded systems’. Design Automation Conf., San Diego, USA, 2004, pp. 275280.
    5. 5)
      • 5. Lie, M., Wang, W.S., Orshansky, M.: ‘Leakage power reduction by dual-Vth designs under probabilistic analysis of Vth variation’. IEEE Int. Symp. on Low Power Electronics and Design, California, USA, 2004, pp. 27.
    6. 6)
      • 6. Jung, H., Pedram, M.: ‘Dynamic power management under uncertain information’. EDA Consortium Conf. on Design, Automation and Test, Nice, France, 2007, pp. 10601065.
    7. 7)
      • 7. Dhiman, G., Rosing, T.S.: ‘System-level power management using online learning’, IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst., 2009, 28, pp. 676689.
    8. 8)
      • 8. Agarwal, Y., Savage, S., Gupta, R.: ‘Sleepserver: a software-only approach for reducing the energy consumption of PCs within enterprise environments’. Usenix Conf. on Usenix Technical Conf., Boston, MA, USA, 2010.
    9. 9)
      • 9. Smullen, C.W., Coffman, J., Gurumurthi, S.: ‘Accelerating enterprise solid-state disks with nonvolatile merge caching’. Int. Conf. on Green Computing, Chicago, IL, USA, 2010, pp. 203214.
    10. 10)
      • 10. Zhu, Y., Mueller, F.: ‘Feedback EDF scheduling of real-time tasks exploiting dynamic voltage scaling’, Real-Time Syst., 2005, 31, pp. 3363.
    11. 11)
      • 11. Azevedo, A., Issenin, I., Cornea, R., et al: ‘Profile-based dynamic voltage scheduling using program checkpoints’. IEEE Conf. on Design, Automation and Test in Europe, Paris, France, 2002, pp. 168175.
    12. 12)
      • 12. Ge, Y., Qiu, Q.: ‘Dynamic thermal management for multimedia application using machine leaning’. IEEE Conf. Design Automation, New York, USA, 2011, pp. 95100.
    13. 13)
      • 13. Chung, E.Y., Micheli, G.D., Benini, L.: ‘Contents provider-assisted dynamic voltage scaling for low energy multimedia applications’. ACM Int. Symp. on Low Power Electronics and Design, Monterey, CA, USA, 2002, pp. 4247.
    14. 14)
      • 14. Tan, Y., Malani, P., Qiu, Q., et al: ‘Workload prediction and dynamic voltage scaling for MPEG decoding’. IEEE Conf. on Design Automation, Yokohama, Japan, 2006, pp. 911916.
    15. 15)
      • 15. Coskun, A.K., Rosing, T.S., Gross, K.C.: ‘Utilizing predictors for efficient thermal management in multiprocessor SoCs’, IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst., 2009, 28, pp. 15031516.
    16. 16)
      • 16. Cai, L., Pettis, N., Lu, Y.: ‘Joint power management of memory and disk under performance constraints’, IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst., 2006, 25, pp. 26972711.
    17. 17)
      • 17. Li, C., Wang, R., Goswami, N., et al: ‘Chameleon: adapting throughput server to time-varying green power budget using online learning’. IEEE Int. Symp. on Low Power Electronics and Design, Beijing, China, 2013, pp. 100105.
    18. 18)
      • 18. Hao, S., Lu, J., Qiu, Q.: ‘Learning based DVFS for simultaneous temperature, performance and energy management’. Int. Symp. on Quality Electronic Design, Santa Clara, CA, USA, 2012, pp. 747754.
    19. 19)
      • 19. Fujishiqe, S.: ‘Submodular functions and optimization’, vol. 58 (Elsevier Science, Elsevier, 2005).
    20. 20)
      • 20. MediaBench: Available at

Related content

This is a required field
Please enter a valid email address