Date of Award

1-13-2016

Degree Type

Thesis

Degree Name

M.Sc.

Department

Computer Science

First Advisor

Jaekel, Arunita

Keywords

Anycast, Energy Efficient, Optical Grids, Sliding Scheduled

Rights

CC BY-NC-ND 4.0

Abstract

Optical grids have been thought as an answer to support large-scale data intensive applications. Data centers and Optical grids are largest and fastest growing consumers of electricity. Energy efficient routing schemes and traffic models can answer the problem of energy consumption. In Optical Grids, it is possible to select destination node from the set of possible destinations which is known as anycasting. We propose ILP formulations for flexible sliding scheduled traffic model, where setup and tear down times may vary within larger window frame. The problem of energy consumption is addressed by switching off ideal network components in low utilization periods. Our proposed novel formulation that exploits knowledge of demand holding times to optimally schedule demands achieved 7-13% reduction in energy consumption compared to previously best known model.

Share

COinS