Abstract
In this study, an adaptive power management method based on reinforcement learning is proposed to improve the energy utilization and battery endurance for resource-limited embedded systems. A simulator which traces battery endurance and device operations is developed to examine the proposed method. Experimental results show that, in terms of battery efficiency and endurance, the performance of our proposed method is better than the traditional power management techniques, such as static power management method.
Keywords
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Benini, L., Bogliolo, A., Micheli, G.: A survey of Design Techniques for System-Level Dynamic Power Management. IEEE Transactions on Very Large Scale Integration Systems 8(3), 299–316 (2000)
Carreras, M., Yuh, J., Batlle, J., Ridao, P.: A Behavior-Based Scheme Using Reinforcement Learning for Autonomous Underwater Vehicles. IEEE Journal of Oceanic Engineering 30(2), 416–427 (2005)
Chen, W.-z., Zheng, H.: Analysis of Power Saving Effect for Dynamic Power Management. In: Proc. of the 2nd IEEE/ASME International Conference, pp. 1–4 (2006)
Cho, Y., Chang, N.: Energy-Aware Clock-Frequency Assignment in Microprocessors and Memory Devices for Dynamic Voltage Scaling. IEEE Transactions on Computer-Aided Design of Integrated Circuits and System 26(6), 1030–1040 (2002)
Chung, E.-Y., Benini, L., Bogliolo, A., Lu, Y.-H., Micheli, G.: Dynamic Power Management for Non-stationary Service Requests. IEEE Transactions on Computers 51(11), 1345–1361 (2002)
Dhiman, G., Rosing, T.S.: Dynamic Power Management Using Machine Learning. In: International Conference on Computer-Aided Design, San Jose, CA (2006)
Ernst, D., Glavic, M., Wehenkel, L.: Power Systems Stability Control: Reinforcement Learning Framework. IEEE Transactions on Power Systems 19(1), 427–435 (2004)
Irani, S., Shukla, S., Gupta, R.: Competitive Analysis of Dynamic Power Management Strategies for Systems with Multiple Power Saving States. In: Proc. of the Design, Automation and Test in Europe Conference and Exhibition (2002)
Li, M., Wu, X., Yao, R., Yan, X.: Q-DPM: An Efficient Model-free Dynamic Power Management Technique. In: Proc. of the Design, Automation and Test in Europe Conference and Exhibition (2005)
Lu, Y.-H., Micheli, G.: Comparing System-Level Power Management Policies. IEEE Transactions Design and Test of Computers 18(2), 10–19 (2001)
Qiu, Q., Wu, Q., Pedram, M.: Stochastic Modeling of a Power-Managed System- Construction and Optimization. IEEE Transactions on Computer-Aided Design of Integrated Circuits and System 20(10), 1200–1217 (2001)
Rong, P., Pedram, M.: Battery-Aware Power Management Based on Markovian Decision Processes. IEEE Transactions on Computer-Aided Design of Integrated Circuits and System 25(7), 1337–1349 (2006)
Cheng, S.-H., Wang, K.: An Adaptive Hybrid Dynamic Power Management Method for Handheld Devices. In: Proc. of the IEEE International Conference on Sensor Networks, Ubiquitous and Trustworthy Computing (2006)
Simunic, T., Benini, L.: Event-Driven Power Management. IEEE Transactions on Computer-Aided Design of Integrated Circuits and System 20(7), 840–857 (2001)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Tynan, R., O’Kane, D.M.D., O’Hare, G.: Agents for Wireless Sensor Network Power Management. In: Proc. of International Conference on Parallel Processing Workshops (2006)
Viswanathan, L.P., Monie, E.C.: Reinforcement Temporal Difference Learning Scheme for Dynamic Energy Management in Embedded Systems. In: Proc. of the 19th International Conference on VLSI Design (2006)
Vlachogiannis, J.G., Hatziargyriou, N.D.: Reinforcement Learning for Reactive Power Control. IEEE Transactions on Power Systems 19(3), 1317–1325 (2004)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Liu, Ct., Hsu, R.C. (2008). Adaptive Power Management Based on Reinforcement Learning for Embedded System. In: Nguyen, N.T., Borzemski, L., Grzech, A., Ali, M. (eds) New Frontiers in Applied Artificial Intelligence. IEA/AIE 2008. Lecture Notes in Computer Science(), vol 5027. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69052-8_54
Download citation
DOI: https://doi.org/10.1007/978-3-540-69052-8_54
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69045-0
Online ISBN: 978-3-540-69052-8
eBook Packages: Computer ScienceComputer Science (R0)