As a research paper, I can not argue with that. But as an engineering paper, trying to adjust routing based on instantaneous load is a known non-starter. But that is what the paper says it does. Which strongly suggests that this problem space is still not ready for engineering. (I am reminded of the wonderfully elegant work on compact routing which could have reduced our routing table size. If only the topology would stay put. But it doesn't.)
I am not saying folks shouldn't do research. they should. Whether such research is even ready for the IRTF is a different question I leave to researchers and the IRSG. Whether we even know what questions to be asking to try to improve the situation in ways that are relevant to the IETF is also a reasonable question. But not one for engineering. If the IAB thinks it can get a good discussion among people at different layers of protocol design and people who actually deal with energy and resource tradeoffs, ,to start working on finding the right questions is up to them.
Yours,
Joel
On 8/6/2022 1:51 AM, Hesham ElBakoury wrote:
Hi Joel,Why IETF does not have the skill set to define extensions to OSPF to be more energy efficient ? Example of such extensions is described in this recent paper https://arxiv.org/pdf/2207.00035.
ThanksHesham
On Fri, Aug 5, 2022, 4:22 PM Joel Halpern <jmh@xxxxxxxxxxxxxxx> wrote:
I can't speak for Fred, but I don't think we as a community even know what "energy efficient protocol" means. Much less how that trades off against all the other aspects of protocol design.
We do consider message size and frequency when we design protocols. We consider those aspects along with lots of others. if that is "designing energy efficient protocols" then we already do so. On the other hand, design for issues such as to to partially wake up a sleeping device is generally outside our remit and skill set. And is meaningless for many of our devices.
Yours,
Joel
On 8/5/2022 7:18 PM, Hesham ElBakoury wrote:
Hi Fred,Do you think IETF engineers have the skill sets to design energy efficient protocols or enhance existing ones to be more energy efficient ?
Thanks,Hesham
On Fri, Aug 5, 2022, 1:22 PM Fred Baker <fredbaker.ietf@xxxxxxxxx> wrote:
Echoing a previous post, I’m not sure sustainability is part of our skill set. If we were to try to forcibly add it, I suspect we’d get the same level of response security originally got: “sustainability is not specified in this document”.
Sent using a machine that autocorrects in interesting ways...
> On Aug 5, 2022, at 2:26 AM, Stewart Bryant <stewart.bryant@xxxxxxxxx> wrote:
>
> Perhaps it is time for a new mandatory section in RFCs: sustainability?
Thank Joel!
The approach used by this paper is an engineering approach. The paper says "The al-gorithm we devised represents our engineering approach to the solution of the well known (though still open) issue of dynamic network topology adaptation to improve energy efficiency."
Also note that the coauthor of this paper is Professor Simon Pietro Romano who is the cofounder of Meetecho. He acively participates in IETF standardization activities.
I think IETF has very smart people; some has relevant skill set, knowledge and expertise to look at infrastructure energy efficiency problems.
As you mentioned, the issue is to find a problem that needs to be solved and the solution should be standardized for customers to deploy it. We can argue whether the solution described in this paper for the well-known infrastructure energy and QoS management problem should be standardized or not. But if it needs to be standardized, I think IETF already has and can bring in the right experts to do the standardization work.
I think Jari's workshop on energy management is a good start to brainstorm what IETF can do to address energy management problems in IP networks. Jari also mentioned during IETF 114 NMRG meeting that IETF should work on energy management.
Thanks
Hesham
On Sat, Aug 6, 2022, 6:48 AM Joel Halpern <jmh.direct@xxxxxxxxxxxxxxx> wrote:
