Site Search
Computer Science

Photos

Lambton TowerLambton Tower
Lambton Tower
Dr. Ziad Kobti lecturingDr. Ziad Kobti
Dr. Ziad Kobti
Robin Gras, Ph.D.Dr. Robin Gras
Dr. Robin Gras
Jessica Chen, Ph.D.Dr. Jessica Chen
Dr. Jessica Chen
Arunita Jaekel, Ph.D.Dr. Arunita Jaekel
Dr. Arunita Jaekel
Christie Ezeife, Ph.D.Dr. Christie Ezeife
Dr. Christie Ezeife
Xiaobu Yuan, Ph.D.Dr. Xiaobu Yuan
Dr. Xiaobu Yuan
Windsor WaterfrontWindsor Waterfront Park
Windsor Waterfront Park
Alioune Ngom, Ph.D.Dr. Alioune Ngom
Dr. Alioune Ngom
Imran Ahmad, Ph.D.Dr. Imran Ahmad
Dr. Imran Ahmad
Dr. Luis RuedaDr. Luis Rueda
Dr. Luis Rueda
Dr. Scott GoodwinDr. Scott Goodwin
Dr. Scott Goodwin
Dr. Robert KentDr. Robert Kent
Dr. Robert Kent

Real-Time Energy Pirce-Aware Anycast RWA for Scheduled Lightpath Demands in Optical Data Center Networks

Add this event into your calendar using the iCAL format
  • Mon, 06/05/2017 - 2:30pm - 4:30pm




Real-Time Energy Price-Aware Anycast RWA for Scheduled Lightpath Demands in Optical Data Center Networks

MSc Thesis Proposal by:

Karan Neginhal

 Date:  Monday, June 5th, 2017
Time:  2:30 pm – 4:30 pm
Location: Essex Hall, #122

Abstract: With the fast rise of large-scale applications, and rapidly growing distributed computing and capacity, the number and size of data centers have increased extensively. Power utility cost is a noteworthy operating expense of data center networks. A little development in energy management can save hundreds of million dollars of electricity cost. Efficient routing schemes and proper combination of the replicas can solve the problem for energy consumption and simultaneously help reduce costs for the data centers. We propose to minimize the electricity costs and energy consumption of a data center network using anycast routing scheme for scheduled traffic demands. We have used the real-time pricing model by considering the price changes throughout the day for the electricity prices. Our proposed approach uses the anycast principle to select the most suitable destination for a given demand. Our approach also takes into consideration energy consumption at the network nodes and along the optical fibers, as well as the start time and duration of each demand. We have developed a new integer linear program (ILP) formulation to solve this integrated routing and scheduling problem. We will check our results on different standard topologies like NFSNET and compare the results for different demand sets. Based on real-time pricing there is an algorithm called the Least Dollar Path (LDP), we will compare our results with this algorithm and a few other routing schemes. We will also consider the flat rate prices and see how our ILP is able to achieve greater savings for electricity costs. 

Thesis Committee:
Internal Reader: Dr. Stephanos Mavromoustakos
External Reader: Dr. Animesh Sarker
Advisor: Dr. Arunita Jaekel

 

 



csgradinfo@uwindsor.ca
(519)253-3000


See More: