Date of Award

2016

Publication Type

Master Thesis

Degree Name

M.Sc.

Department

Computer Science

First Advisor

Bandyopadhyay, Subir

Second Advisor

Aneja, Yash

Keywords

Data centers, Disaster-resilient network, Fault tolerant, Integer Linear Programming, OFDM network, Optical networks

Rights

info:eu-repo/semantics/openAccess

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Abstract

With the ever-increasing need for faster data communication, cloud services using datacenters are becoming the norm for large-scale data processing. When a disaster occurs in such a system, it is important to ensure that the users do not experience a huge data loss. Current techniques based on protection or restoration are not appropriate for such systems. Recently, the use of Orthogonal Frequency Division Multiplexing (OFDM) has been proposed for high bandwidth demands in cloud networks. Techniques for handling disasters in OFDM networks have not been investigated yet. A new scheme is developed in this research for recovering from any disaster by switching over to alternate paths that avoid the disaster. A new Integer Linear Programming (ILP) formulation has been developed, based on this scheme. The proposed formulation gives an optimal solution, based on an exhaustive search and is useful as a benchmark. A number of experiments have been conducted, which demonstrate the feasibility of the approach.

Download

Share

COinS