The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.12 - Dec. (2012 vol.61)
pp: 1789-1799
Lykomidis Mastroleon , Stanford University, Stanford
Daniel C. O'Neill , Stanford University, Stanford
Benjamin Yolken , Stanford University, Stanford
Nicholas Bambos , Stanford University, Stanford
ABSTRACT
Due to increasing circuit densities and data throughput rates, power consumption has become a significant concern in the design and operation of high-performance packet switches. We extend the idea of Dynamic Power Management (DPM) to input queued switches, allowing operators to tradeoff power and delay in a useful way. We frame the problem as a dynamic program and solve a relaxation using techniques from Linear Quadratic Regulation (LQR). This optimal policy is combined with existing, nonpower-aware switch controls to generate two novel scheduling algorithms: 1) LQR Power Aware Maximum Weight Matching (LQR PA MWM) and 2) LQR Power Aware Projective Cone Scheduling (LQR PA PCS). Simulation results suggest that our algorithms result in significant power savings compared to MWM and previous power control schemes with little performance degradation.
INDEX TERMS
Energy efficiency, Energy management, Power system management, Throughput, Routing protocols, network management, Routing, power management
CITATION
Lykomidis Mastroleon, Daniel C. O'Neill, Benjamin Yolken, Nicholas Bambos, "Power and Delay Aware Management of Packet Switches", IEEE Transactions on Computers, vol.61, no. 12, pp. 1789-1799, Dec. 2012, doi:10.1109/TC.2011.191
REFERENCES
[1] "Power and Cooling in the Data Center," technical report, AMD Corporation, 2005.
[2] J.G. Koomey, "Estimating Total Power Consumption by Servers in the U.S. and the World," technical report, Lawrence Berkeley Nat'l Laboratory and Stanford Univ., Feb. 2007.
[3] "Report to Congress on Server and Data Center Energy Efficiency Public Law 109-431," US Environmental Protection Agency ENERGY STAR Program.
[4] L. Benini, A. Bogliolo, and G. De Micheli, "A Survey of Design Techniques for System-Level Dynamic Power Management," IEEE Trans. Very Large Scale Integration (VLSI) Systems, vol. 8, no. 3, pp. 299-316, June 2000.
[5] O. Azizi, A. Mahesri, B. Lee, S. Patel, and M. Horowitz, "Energy-Performance Tradeoffs in Processor Architecture and Circuit Design: A Marginal Cost Analysis," Proc. 37th Ann. Int'l Symp. Computer Architecture, pp. 26-36, 2010.
[6] O. Azizi, A. Mahesri, J. Stevenson, S. Patel, and M. Horowitz, "An Integrated Framework for Joint Design Space Exploration of Microarchitecture and Circuits," Proc. Design, Automation and Test in Europe Conf. and Exhibition (DATE), pp. 250-255, 2010.
[7] "Addressing Power and Thermal Challenges in the Datacenter," technical report, Intel Corporation, 2004.
[8] C. Minkenberg, R.P. Luijten, F. Abel, W. Denzel, and M. Gusat, "Current Issues in Packet Switch Design," ACM SIGCOMM, vol. 33, no. 1, pp. 119-124, Jan. 2003.
[9] N. Bambos and D. O'Neill, "Power Management of Packet Switch Architectures with Speed Modes," Proc. Allerton Conf. Comm., Control and Computing, Oct. 2003.
[10] A. Dua, B. Yolken, and N. Bambos, "Power Managed Packet Switching," Proc. IEEE Int'l Conf. Comm., June 2007.
[11] K. Ross and N. Bambos, "Local Search Scheduling Algorithms for Maximal Throughput in Packet Switches," Proc. IEEE INFOCOM, pp. 1158-1169, Mar. 2004.
[12] K. Ross and N. Bambos, "Projective Cone Scheduling (PCS) Algorithms for Packet Switches of Maximal Throughput," IEEE/ACM Trans. Networking, vol. 17, no. 3, pp. 976-989, June 2009.
[13] M. Armony and N. Bambos, "Queueing Dynamics and Maximal Throughput Scheduling in Switched Processing Systems," Queueing Systems: Theory and Applications, vol. 44, no. 3, pp. 209-252, 2003.
[14] L. Mastroleon, "Admissible Traces, Stability and Rate Management of Queueing/Switching Service Structures," Proc. IEEE INFOCOM, pp. 2016-2024, Apr. 2009.
[15] D.R. Avresky, V. Shubranov, R. Horst, and P. Mehra, "Performance Evaluation of the Servernet San under Self-Similar Traffic," Proc. 13th Int'l Symp. Parallel Processing and 10th Symp. Parallel and Distributed Processing, pp. 143-147, Apr. 1999.
41 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool