Abstract
Energy consumption represents a large percentage of the operational expenses in data centers. Most of the existing solutions for energy-aware scheduling are focusing on job distribution and consolidation between computing servers, while network characteristics are not considered. In this paper, we propose a model of power and network-aware scheduling that can be tuned to achieve energy-savings, through job consolidation and traffic load balancing. We describe a methodology to find the best tuning of the Adjustable Scheduler. © 2016 IEEE.
Original language | English |
---|---|
Pages | 29-33 |
Number of pages | 5 |
DOIs | |
Publication status | Published - 2017 |
Event | 9th International Conference on Engineering and Telecommunication, - Moscow, Russian Federation Duration: 29 Nov 2016 → 30 Nov 2016 |
Conference
Conference | 9th International Conference on Engineering and Telecommunication, |
---|---|
Abbreviated title | EnT 2016 |
Country/Territory | Russian Federation |
City | Moscow |
Period | 29/11/16 → 30/11/16 |
Keywords
- Data center
- Energy efficient
- Parallel machines
- Scheduling algorithms
- Energy conservation
- Energy efficiency
- Energy utilization
- Scheduling
- Data centers
- Energy-aware scheduling
- Network characteristics
- Network-Aware Scheduling
- Operational expense
- Parallel machine
- Traffic loads
- Power management