MASTER OF SCIENCE THESIS DEFENSE BY: Massarrah Tannous
When: Tuesday,
June 9, 2015
1:00 PM
-
3:00 PM
Where: Science & Engineering Building, Lester W. Cory Conference Room: Room 213A
Cost: free
Description: TOPIC: RELIABILITY MODELING AND EVALUATION OF MESH TOPOLOGY IN STORAGE AREA NETWORKS
LOCATION: Lester W. Cory Conference Room, Science & Engineering Building (Group II), Room 213A
ABSTRACT:
Storage area networks (SANs) have critical applications such as financial services, medical services and electronic commerce. To meet high reliability and availability requirements of these applications, SANs have to provide fault tolerance through redundancy to minimize or eliminate system downtime, thus preventing business discontinuity due to catastrophic events. Mesh is one of the SAN topologies that have been applied to implement a fault tolerant SAN.
In this thesis, failure behavior of a mesh SAN is first modeled using Dynamic Fault Trees (DFT). Based on the constructed DFT model, reliability of the mesh SAN is evaluated using a binary-decision diagram (BDD) based method, where the BDD is generated and evaluated through Python scripts. The mesh SAN is also modeled using a network graph in order to consider link failures. The constructed graph is converted into a BDD and evaluated using a Java application. A comparison of reliability using the two models is conducted, showing effects of link reliability on the performance of the entire SAN. This thesis work provides insight into the behavior of a mesh SAN system and further provides guidelines in the reliable design and operation of SANs.
NOTE: All ECE Graduate Students are ENCOURAGED to attend.
All interested parties are invited to attend. Open to the public.
Advisor: Dr. Liudong Xing
Committee Members: Dr. Honggang Wang, Department of Electrical & Computer Engineering and Dr. Haiping Xu, Department of Computer and Information Science
*For further information, please contact Dr. Liudong Xing at 508.999.8883, or by via email at lxing@umassd.edu.
LOCATION: Lester W. Cory Conference Room, Science & Engineering Building (Group II), Room 213A
ABSTRACT:
Storage area networks (SANs) have critical applications such as financial services, medical services and electronic commerce. To meet high reliability and availability requirements of these applications, SANs have to provide fault tolerance through redundancy to minimize or eliminate system downtime, thus preventing business discontinuity due to catastrophic events. Mesh is one of the SAN topologies that have been applied to implement a fault tolerant SAN.
In this thesis, failure behavior of a mesh SAN is first modeled using Dynamic Fault Trees (DFT). Based on the constructed DFT model, reliability of the mesh SAN is evaluated using a binary-decision diagram (BDD) based method, where the BDD is generated and evaluated through Python scripts. The mesh SAN is also modeled using a network graph in order to consider link failures. The constructed graph is converted into a BDD and evaluated using a Java application. A comparison of reliability using the two models is conducted, showing effects of link reliability on the performance of the entire SAN. This thesis work provides insight into the behavior of a mesh SAN system and further provides guidelines in the reliable design and operation of SANs.
NOTE: All ECE Graduate Students are ENCOURAGED to attend.
All interested parties are invited to attend. Open to the public.
Advisor: Dr. Liudong Xing
Committee Members: Dr. Honggang Wang, Department of Electrical & Computer Engineering and Dr. Haiping Xu, Department of Computer and Information Science
*For further information, please contact Dr. Liudong Xing at 508.999.8883, or by via email at lxing@umassd.edu.
Contact:
ECE: Electrical & Computer Engineering Department 508.999.9164 http://www.umassd.edu/engineering/ece/
Topical Areas: General Public, University Community, Electrical and Computer Engineering