Date of Award
10-5-2017
Publication Type
Master Thesis
Degree Name
M.Sc.
Department
Computer Science
Supervisor
Jaekel, Arunita
Rights
info:eu-repo/semantics/openAccess
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Abstract
The energy consumption of the data center networks and the power consumption associated with transporting data to the users is considerably large, and it constitutes a significant portion of their costs. Hence, development of energy efficient schemes is very crucial to address this problem. Our research considers the fixed window traffic allocation model and the anycast routing scheme to select the best option for the destination node. Proper routing schemes and appropriate combination of the replicas can take care of the issue for energy utilization and at the same time help diminish costs for the data centers. We have also considered the real-time pricing model (which considers price changes every hour) to select routes for the lightpaths. Hence, we propose an ILP to handle the energyaware routing and wavelength assignment (RWA) problem for fixed window scheduled traffic model, with an objective to minimize the overall electricity costs of a datacenter network by reducing the actual power consumption, and using low-cost resources whenever possible.
Recommended Citation
Neginhal, Karan, "Real-Time Energy Price-Aware Anycast RWA for Scheduled Lightpath Demands in Optical Data Center Networks" (2017). Electronic Theses and Dissertations. 7284.
https://scholar.uwindsor.ca/etd/7284