Abstract: Deployment architecture is the mapping of a system's software components onto its hardware 'platforms. For any large, distributed system, many deployment architectures will be typically possible that provide the same functionality. However, some deployment architectures will provide better quality of service (QoS) than others. For this reason, a system's deployment architecture will influence the users' satisfaction, as users typically have varying QoS preferences for the system services they access. Finding a deployment architecture that will maximize the users' overall satisfaction is a challenging, multi-faceted problem. In this talk, we present a framework and a set of generic algorithms that can be tailored and instantiated to address this problem. The framework relies on users' (desired) degree of satisfaction with QoS improvements to resolve trade-offs between conflicting QoS dimensions. The framework is realized on top of an integrated tool suite, which is composed of a visual software deployment modeling and analysis environment, and a middleware platform for runtime monitoring and (re)deployment of a software system. The results of applying the framework on a large number of application scenarios have been very positive, in some cases producing up to an order of magnitude improvement in certain QoS dimensions. The framework has also been evaluated on several real distributed systems in collaboration with industrial partners, and has recently been adopted for use by a large embedded systems development organization.

Short Bio: Sam Malek is a Ph.D. candidate in Computer Science at the University of Southern California, where he has been a research assistant in the Center for Systems and Software Engineering since 2003. While his general research interests are in the field of software engineering, his focus has spanned the areas of software architecture, distributed and embedded software systems, and quality of service analysis. The underlying theme of his research has been to devise techniques and tools that aid with the construction, analysis, and maintenance of large-scale distributed and embedded software systems. He has received a M.S. degree in Computer Science from the University of Southern California, and a B.S. degree in Information and Computer Science from the University of California Irvine.