ABSTRACT
Sleeping is an important method to reduce energy consumption in many information and communication systems. In this paper we focus on a typical server under dynamic load, where entering and leaving sleeping mode incurs an energy and a response time penalty. We seek to understand under what kind of system configuration and control method will sleep mode obtain a Pareto Optimal tradeoff between energy saving and average response time. We prove that the optimal "sleeping" policy has a simple hysteretic structure. Simulation results then show that this policy results in significant energy savings, especially for relatively delay insensitive applications and under low traffic load. However, we demonstrate that seeking the maximum energy saving presents another tradeoff: it drives up the peak temperature in the server, with potential reliability consequences.
- F. Baccelli, S. Machiraju, D. Veitch and J. C. Bolot. The role of PASTA in network measurement. In ACM SIGCOMM, 2006. Google ScholarDigital Library
- N. Bansal, T. Kimbrel, K. Pruhs. Speed scalaing to manage energy and temperature. J. ACM 54(1), 2007. Google ScholarDigital Library
- L. A. Barroso and U. Hölzle. The Case for Energy-Proportional Computing. Computer. 40(12):33--37, 2007. Google ScholarDigital Library
- D. P. Bertsekas. Dynamic Programming and Optimal Control, volume 2. Athena Scientific, Belmont, MA, USA, 2007. Google ScholarDigital Library
- P. Bohrer, E. Elnozahy, T. Keller, M. Kistler, C. Lefurgy and R. Rajamony. The case for power management in web servers. In Power Aware Computing. January 2002. Google ScholarDigital Library
- J. C. Cardona Restrepo, C. G. Gruber and C. Mas Machuca. Energy Profile Aware Routing. In Proc. Green Communications Workshop in conjuction with IEEE ICC'09 (GreenComm09). Dresden, Germany, 2009.Google Scholar
- L. Chiaraviglio, M. Mellia and F. Neri. Reducing Power Consumption in Backbone Networks. In Proc. 2009 IEEE Internat. Conf. on Communications (ICC 2009). Dresden, Germany, 2009. Google ScholarDigital Library
- A. K. Coşkun, T. S. Rosing, K. A. Whisnant and K. C. Gross. Static and dynamic temperatur-aware scheduling for multiprocessor SoCs. IEEE Trans. VLSI, 16(9):1127--1140, 2008. Google ScholarDigital Library
- X. Fan, W-D. Weber, and L. A. Barroso. Power Provisioning for a Warehouse-sized Computer. In Proceedings of the ACM International Symposium on Computer Achitecure. San Diego, CA, June 2007. Google ScholarDigital Library
- J. M. George, and J. M. Harrison. Dynamic Control of a Queue with Adjustable Service Rate.INFORMS Operations Research. 49(5):720--731, September--October 2001. Google ScholarDigital Library
- M. Gupta and S. Singh. Greening of the Internet. In ACM SIGCOMM. Karlsruhe, Germany, August 2003. Google ScholarDigital Library
- M. Hersh and I Brosh. The optimal strategy structure of an intermitently operating service channel. European Journal of the Operational Research Society. 5:133--141, 1980.Google ScholarCross Ref
- D. P. Heyman Optimal operating policies for M/G/1 queueing systems Operations Research. 16:362--382, 1968.Google Scholar
- S. K. Hipp, and U. D. Holzbaur. Decision Processes with Monotone Hysteretic Policies. Operations Research. 36(4):585--588, July--August 1988. Google ScholarDigital Library
- H. Kim and G. de Veciana. Leveraging dynamic spare capacity in wireless systems to conserve mobile terminals energy. to appear in IEEE/ACM Trans. Networking. Google ScholarDigital Library
- M. Kodialam, T. V. Lakshman and S. Sengupta. Traffic-oblivious routing for guaranteed bandwidth performance. IEEE Comm. Mag., pages 46--51. 2007. Google ScholarDigital Library
- S. Nedevschi, L. Popa, G. Iannaccone, S. Ratnasamy and D. Wetherall. Reducing Network Consumption via Sleeping and Rate-Adaptation. 2007.Google Scholar
- F. V. Lu and R. F. Serfozo. M/M/1 Queueing Decision Processes with Monotone Hysteretic Optimal Policies. In Operations Research. 32(5), September--October 1984.Google Scholar
- J. Mogul. Improving energy efficiency for networked applications. In Architectures for Networking and Communications Systems (ANCS). 2007Google Scholar
- D. Meisner, B. T. Gold and T. F. Wenisch. PowerNap: eliminating server idle power. In ASPLOS '09: Proceeding of the 14th international conference on Architectural support for programming languages and operating systems, pages 205--216. 2009. Google ScholarDigital Library
- K. Pruhs, P. Uthaisombut and G. Woeginger. Getting the best response for your erg. In Scandinavian Worksh. Alg. Theory. 2004Google Scholar
- N. Vasic and D. Kostic. Energy-Aware Traffic Engineering. In EPFL Technical Report NSL-REPORT-2008-004. 2008.Google Scholar
- A. Wierman, L. Andrew and A. Tang. Power-Aware Speed Scaling in Processor Sharing Systems. In Proc. IEEE INFOCOM. April 2009.Google ScholarCross Ref
- R. W. Wolff. Poisson arrivals see time averages. Operations Research. 30(2):223--231, 1982.Google ScholarDigital Library
- M. Yadin and P. Naor. Queueing systems with a removalbe service station. Operations Research, 14(4):393--405, 1963.Google ScholarCross Ref
- F. Yao, A. Demers and S. Shenker. A scheduling model for reduced CPU energy. In Proc. IEEE Symp. Foundations of Computer Science (FOCS), pages 374--382. 1995. Google ScholarDigital Library
- M. Yu, Y. Yi and J. Rexford and M. Chiang. Rethinking virtual network embedding: Substrate support for path splitting and migration. ACM SIGCOMM Computer Communications Review. 38(2):19--29, 2008. Google ScholarDigital Library
- B. Zhai, D. Blaauw, D. Sylvester and K. Flautner. Theoretical and practical limits of dynamic voltage scaling. In DAC. 2004. Google ScholarDigital Library
- Z. G. Zhang, E. Love and Y. Song. The optimal service time allocation of a versatile server to queue jobs and stochastically available non-queue jobs of different types. Computers and Operations Research. 34(6):1857--1870, 2007.Google ScholarCross Ref
Index Terms
- Optimal sleep patterns for serving delay-tolerant jobs
Recommendations
Enhanced sleep mode operations for energy saving in IEEE 802.16e
EUC'07: Proceedings of the 2007 conference on Emerging direction in embedded and ubiquitous computingThe broadband wireless access (BWA) network, such as IEEE 802.16e, becomes more and more popular in recent years. According to the IEEE 802.16e specifications, mobile subscriber stations (MSSs) with energy constraints are allowed to switch to the sleep ...
Power-saving strategy for balancing energy and delay performance in WLANs
In wireless local area networks (WLANs), power conservation for mobile devices is considered as one of the most important issues because it effectively prolongs the battery life of mobile devices. The IEEE 802.11 standard specifies a power-saving mode ...
Characterizing Energy–Delay Tradeoff in Hyper-Cellular Networks With Base Station Sleeping Control
Base station (BS) sleeping operation is one of the effective ways to save energy consumption of cellular networks, but it may lead to longer delay to the customers. The fundamental question then arises: How much energy can be traded off by a tolerable ...
Comments