Similar articles

Abstract: The mass of the embedded systems are driven by second batteries, not by wired power supply. So saving energy is one of the main design goals for embedded system. In this paper we present a new technique for modelling and solving the dynamic power management (DPM) problem for embedded systems with complex behavioural characteristics. First we model a power-managed embedded computing system as a controllable flow Chart. Then we use the poisson process for optimisation, and give the power management algorithm by the help of Dynamic Voltage Scaling (DVS) technology. At last we built the experimental model using the PXA 255 Processors. The experimental results showed that the proposed technique can achieve more than 12% power saving compared to other existing DPM techniques.

[1] Balakrishnan, N., Basu, A.P., 1996. The Exponential Distribution: Theory, Methods, and Applications. Gordon and Breach, New York.

[2] Cai, L., Lu, Y.H., 2004. Dynamic Power Management Using Data Buffers. School of Electrical and Computer Engineering, Purdue University.

[3] Huang, J.W., Chen, T.Z., Lian, Y., Dai, H.J., 2004a. Dynamic Power Management of Complex System Using Flow Model and Passion Process. IASTED International Conference on Power and Energy Systems (PES 2004).

[4] Huang, J.W., Chen, T.Z., Ye, M.J., Yi, L., 2004b. Dynamic Power Management of Complex Systems Using Flow Model. The First International Conference on Embedded Software and System (ICESS 2004).

[5] Li, D.X., Xie, Q., Pai, H., 2003. Scalable Modeling and Optimization of Mode Transitions Based on Decoupled Power Management Architecture. Irvine, Chou Center for Embedded Computer Systems University of California.

[6] Paleologo, G.A., Benini, L., Bogliolo, A., Micheli, G.D., 1998. Policy Optimization for Dynamic Power Management. Proceedings of Design Automation Conference, p.182-187.

[7] Papoulis, A., 1984. Poisson Process and Shot Noise. Ch.16 in Probability, Random Variables, and Stochastic Processes, 2nd Ed. McGraw-Hill, New York, p.554-576.

[8] Pfeiffer, P.E., Schum, D.A., 1973. Introduction to Applied Probability. Academic Press, New York.

[9] Qiu, Q.R., Pedram, M., 1999. Dynamic Power Management Based on Continuous-Time Markov Decision Processes. Annual ACM IEEE Design Automation Conference, Proceedings of the 36th ACM/IEEE Conference on Design Automation. New Orleans, Louisiana, United States, p.555-561.

[10] Qiu, Q.R., Wu, Q., Massoud, P., 2000. Dynamic Power Management of Complex Systems Using Generalized Stochastic Petri Nets. Department of Electrical Engineering

[11] Viredaz, M.A., Wallach, D.A., 2004. Power evaluation of a handheld computer. IEEE Micro, 23(1):2003.

[12] Weisstein, E.W., 2000. Poisson Distribution. http://mathworld.wolfram.com/PoissonDistribution.html.