Reducing Network Energy Consumption via Rate-Adaptation and Sleeping

Sergiu Nedevschi, Lucian Popa, Gianluca Iannaccone, Sylvia Ratnasamy and David Wetherall

EECS Department
University of California, Berkeley
Technical Report No. UCB/EECS-2007-128
October 29, 2007

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2007/EECS-2007-128.pdf

We present the design and evaluation of two forms of power management schemes that reduce the energy consumption of networks. The first is based on adapting the rate of network operation to the offered workload, reducing the energy consumed when actively processing packets. The second is based on putting network components to sleep during idle times, reducing energy consumed in the absence of packets.

Using real-world network topologies and traffic workloads, we show that: (1) even simple schemes for sleeping or rate-adaptation can offer substantial savings without significantly degrading network performance and (2) both forms of solutions are valuable depending (primarily) on the power profile of network equipment and the utilization of the network itself.


BibTeX citation:

@techreport{Nedevschi:EECS-2007-128,
    Author = {Nedevschi, Sergiu and Popa, Lucian and Iannaccone, Gianluca and Ratnasamy, Sylvia and Wetherall, David},
    Title = {Reducing Network Energy Consumption via Rate-Adaptation and Sleeping},
    Institution = {EECS Department, University of California, Berkeley},
    Year = {2007},
    Month = {Oct},
    URL = {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2007/EECS-2007-128.html},
    Number = {UCB/EECS-2007-128},
    Abstract = {We present the design and evaluation of two forms of power management schemes that reduce the energy consumption of networks. The first is based on adapting the rate of network operation to the offered workload, reducing the energy consumed when actively processing packets. The second is based on putting network components to sleep during idle times, reducing energy consumed in the absence of packets.

Using real-world network topologies and traffic workloads, we show that: (1) even simple schemes for sleeping or rate-adaptation can offer substantial savings without significantly degrading network performance and (2) both forms of solutions are valuable depending (primarily) on the power profile of network equipment and the utilization of the network itself.}
}

EndNote citation:

%0 Report
%A Nedevschi, Sergiu
%A Popa, Lucian
%A Iannaccone, Gianluca
%A Ratnasamy, Sylvia
%A Wetherall, David
%T Reducing Network Energy Consumption via Rate-Adaptation and Sleeping
%I EECS Department, University of California, Berkeley
%D 2007
%8 October 29
%@ UCB/EECS-2007-128
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2007/EECS-2007-128.html
%F Nedevschi:EECS-2007-128