Reducing the Energy Consumption of Ethernet with Adaptive Link Rate (ALR)

Abstract

Abstract-The rapidly increasing energy consumption by computing and communications equipment is a significant economic and environmental problem that needs to be addressed. Ethernet network interface controllers (NICs) in the US alone consume hundreds of millions of US dollars in electricity per year. Most Ethernet links are underutilized and link energy consumption can be reduced by operating at a lower data rate. In this paper, we investigate Adaptive Link Rate (ALR) as a means of reducing the energy consumption of a typical Ethernet link by adaptively varying the link data rate in response to utilization. Policies to determine when to change the link data rate are studied. Simple policies that use output buffer queue length thresholds and fine-grain utilization monitoring are shown to be effective. A Markov model of a state-dependent service rate queue with rate transitions only at service completion is used to evaluate the performance of ALR with respect to the mean packet delay, the time spent in an energy-saving low link data rate, and the oscillation of link data rates. Simulation experiments using actual and synthetic traffic traces show that an Ethernet link with ALR can operate at a lower data rate for over 80 percent of the time, yielding significant energy savings with only a very small increase in packet delay.

Greening the NetFPGA Reference Router

“…The sampling period is extremely sensitive, because it directly determines the delay between the request for a new frequency and the actual frequency transition. Experimental results indicate that 10 ms is a reasonable interval time for the sampling period and is consistent with that used in implementing ALR [1]. The preset thresholds are adopted to divide the routing capacity into five grades in response to the incoming traffic load in the previous 10-ms sampling period.…”

“…The auto-negotiation scheme in the 802.3 standard takes about 100 ms to change data rates at a 1-Gb/s link data rate. Gunaratne et al [1] proposed the adaptive link rate (ALR) that allows the speed of network links to be changed by adaptively switching to different processing states in response to the amount of data that is being transmitted.…”

“…Because the statistics monitoring is implemented by counting bytes at a fixed sampling period and the statistics may vary slightly from time to time, thus T j must be set lower than C j , and experiments indicate that a reasonable value for T j is 95% of C j . A level of 95% was chosen for consistency with prior work on ALR [1], as was the 10-ms sampling period. The choice of these parameters involves a trade-off between energy savings and packet loss.…”

“…All four ports are used to measure the RTT: two ports of the PG are connected directly to one another, and the RTT is measured to provide a baseline RTT reference as RTT 0 ; the other two ports of the PG are connected to the RR or the FSR under test; and the RTT is measured as RTT 1 . The RTT is calculated as the difference between RTT 1 and RTT 0 .…”

“…Power consumption, while given some attention, failed to be recognized as an important part of a family of design metrics, along with performance, reliability, security, etc. There are approximately one billion Ethernet connections all over the world [1]. The network devices were designed to translate improvements in digital circuits and operating frequency into performance, such as maximizing the router capacity at the cost of the highest and constant power consumption regardless of the traffic load.…”