[LINK] Can a web server be powered by a wind turbine?

[Tom Worthington]

Adrian Chadd wrote:
> On Tue, May 18, 2010, Tom Worthington wrote:
> 
>> It is easier to reduce the load of a web server, than a database server ...
> 
> I don't agree with this particular take on web services being simpler
> than database services, or the reverse. ...

Yes, if you are using the web for providing "web services", then this is 
as complex as a database system. But I had in mind a simple web server, 
serving up static web pages.

> Increasing software efficiency doesn't give as much savings? ...

Yes, as well as software efficiency, I suspect that designing efficient 
web content could increase power efficiency, as much as 100 times. But I 
have to craft student research topics to suit the interests of the 
students. In this case the student has an engineering background, so the 
project has more of a hardware flavour, not web design or software 
efficiency.

> Targetting more efficient platforms with less complicated predictive/
> out-of-order/speculative-preduction/etc; slower memory/IO;etc -
> this doesn't give as much savings? ...

Operating systems can be optimised to produce a more efficient system 
and there are people in the offices around me at ANU doing research into 
that. But this project is not about that, it is about being able to 
change the amount of power the server is drawing to match what is 
available. The idea is to be able to make use of energy sources which 
fluctuate rapidly, particualrly renewable energy.

> Do you have any further references to read?

There will be references provided with the presentation, at the
Australian National University, in Canberra, 18 May 2010:
<http://blog.tomw.net.au/2010/05/wind-powered-web-server.html>.


-- 
Tom Worthington FACS CP HLM, TomW Communications Pty Ltd. t: 0419496150
PO Box 13, Belconnen ACT 2617, Australia  http://www.tomw.net.au
Adjunct Lecturer, The Australian National University t: 02 61255694
Computer Science http://cs.anu.edu.au/user/3890