Network-capable IT electronic equipment consumes at least 75 terawatt-hours per year in the United States alone, producing roughly the same amount of carbon dioxide emissions as 12 million cars. In an attempt to reduce that energy consumption, the IEEE has formed a study group to determine the need and feasibility of producing a standard for energy-efficient Ethernet (EEE). The study group envisions developing a protocol to rapidly change speeds during periods of low link utilization in order to reduce energy use.

Mike Bennett is a senior network engineer at Lawrence Berkeley National Laboratory, and the chairman of the IEEE 802.3 energy-efficient Ethernet study group.

Bruce Nordman is a researcher at Lawrence Berkeley National Laboratory with more than 20 years of experience in energy use and efficiency in electronics and buildings. For additional information: http://efficientnetworks.
lbl.gov/

Lower-speed physical layer devices (PHYs) use less energy than higher-speed PHYs. The group estimates that approximately $300 million per year can be saved through the use of EEE in the United States, assuming existing copper Ethernet devices were replaced with energy-efficient ones.

Changing speeds is not new to Ethernet. The existing Ethernet protocol for changing speeds–auto-negotiation–selects the highest speed in common between link partners. Once the speed has been determined, it cannot be changed without dropping the link.

In contrast, dynamic EEE speed changes should be transparent to upper layers and should happen quickly. Additionally, for EEE to be successful, the frequency of changes and duration at a particular speed must be controlled in such a way that it is non-disruptive. The study group has been exploring mechanisms for speed changes, but the policies to control those changes will be developed by vendors or other standards organizations.

The study group examined developing energy-efficient versions of Ethernet that operate on unshielded twisted-pair cabling and backplanes. The key question to be answered is how fast does transition time (i.e., the transition between speeds) need to be?

The group used one millisecond as a starting point to study the problem. Initial tests, simulating changes from a lower speed to 10GBASE-T as the worst case, suggested a millisecond was too aggressive and the transition time would have to be in the order of tens of milliseconds. Concern that the longer transition time would be noticeable in latency-sensitive applications motivated more in-depth study of the problem.

There are two mechanisms under consideration for EEE twisted-pair PHYs. The “fast start” mechanism is based on existing PHYs and would require minimal changes. Reduction of transition time would come from optimizing the training time–the period when the master and slave link partners exchange information about their states and link characteristics. Additional experiments simulating the low-to-high worst-case speed change suggest transition times in the order of a few milliseconds are feasible.

The second mechanism, known as the “subset-PHY,” requires modification of an existing PHY to operate at a lower speed. For example, a 10GBASE-T PHY would be adapted to operate in a gigabit mode by changing the line code, reducing the number of channels and using rate-matching techniques such as zero stuffing. The signaling would remain the same to minimize changes in crosstalk characteristics.

Initial studies of this mechanism suggest transition times in the order of microseconds are feasible; however, more work would be required to produce the standard and new components. The mechanisms under consideration for backplane Ethernet are similar to their twisted-pair counterparts; however, the comprehensive work to develop the standard is just beginning.

The study group has examined the markets in which EEE could be used, as well as the economic and technical feasibility of developing the protocol. In addition to studying the issues related to transition time, the group studied the impact EEE might have on higher layers.

If the IEEE standards committee approves the project, the first meeting of the IEEE 802.3az task force will be in November. The focus of the work will shift from feasibility study to determining the technical baseline proposal for the standard. Once this proposal has been accepted by the task force, the process of writing the standard will begin. The estimated completion date for IEEE 802.3az is March 2010.