Staged request routing for reduced carbon footprints of large scale server systems
Paper
Paper/Presentation Title | Staged request routing for reduced carbon footprints of large scale server systems |
---|---|
Presentation Type | Paper |
Authors | |
Author | Kist, Alexander A. |
Editors | Frater, Michael |
Journal or Proceedings Title | Proceedings of the Australasian Telecommunication Networks and Applications Conference (ATNAC 2009) |
ERA Conference ID | 50278 |
Number of Pages | 5 |
Year | 2009 |
Place of Publication | Piscataway, NJ. United States |
ISBN | 9781424473236 |
9781424473229 | |
Digital Object Identifier (DOI) | https://doi.org/10.1109/ATNAC.2009.5464964 |
Web Address (URL) of Paper | http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5464964 |
Conference/Event | Australasian Telecommunication Networks and Applications Conference (ATNAC 2009) |
Australasian Telecommunication Networks and Applications Conference | |
Event Details | Australasian Telecommunication Networks and Applications Conference (ATNAC 2009) Event Date 09 to end of 11 Nov 2009 Event Location Canberra, Australia |
Event Details | Australasian Telecommunication Networks and Applications Conference ATNAC |
Abstract | The power consumption of server systems used as part of online services is an important problem as these have become major energy users. Generally, such systems are dimensioned for peak loads and typically have average utilisations of 20-30%. This paper introduces a simple routing mechanism that uses overflow techniques to assign requests to these servers. As these mechanisms employ a staged process, idle systems can be suspended. For a rising number of servers, this yields a load proportional power profile.Request distribution is implemented by a router device; servers report their utilisation to the router. Idle systems suspend their operation; suspended systems are returned to the active state by the Wake-on-LAN function. The system design, performance models and initial results are presented. |
Keywords | routing; carbon footprint; energy efficient computing; load proportional power consumption; performance modelling; cooling; energy consumption; large-scale systems; network servers; power engineering and energy; power system management; power system modeling; web server |
ANZSRC Field of Research 2020 | 400604. Network engineering |
400805. Electrical energy transmission, networks and systems | |
Public Notes | © 2009 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
Byline Affiliations | Department of Electrical, Electronic and Computer Engineering |
https://research.usq.edu.au/item/9z655/staged-request-routing-for-reduced-carbon-footprints-of-large-scale-server-systems
2022
total views119
total downloads1
views this month0
downloads this month