Application-driven overlay network as a service for data-intensive science
Abstract
[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT AUTHOR'S REQUEST.] Campuses are increasingly adopting hybrid cloud architectures for supporting data-intensive science applications that require "on-demand" resources, which are not always available locally on-site. Policies at the campus edge for handling multiple such applications competing for remote resources can cause bottlenecks across applications. These bottlenecks can be proactively avoided with pertinent profiling, monitoring and control of application flows using the emerging paradigm of software-defined networking (SDN). In this thesis, we leverage SDN principles in the design and implementation of an "Applicationdriven Overlay Network-as-a-Service" (ADON) framework that can manage the hybrid cloud requirements of multiple applications in a scalable and extensible manner. ADON's main features include: programmable "custom templates" and a "virtual tenant handler" algorithm. Our solution approach in ADON involves realtime dynamic policy control that ensures predictable application performance delivery. Lastly, we discuss ADON effectiveness validation with an implementation on a wide-area overlay network testbed featuring temporal behavior of research application flows. We conclude by presenting hybrid cloud implementation best practices that ease the orchestration of network programmability for campus network providers and data-intensive application users.
Degree
M.S.
Thesis Department
Rights
Access is limited to the University of Missouri--Columbia.