PRECISE Seminar: Allocation, Isolation & Dynamics in Compositional RT Systems & Applications to Control System Design

PRECISE Seminar: Allocation, Isolation & Dynamics in Compositional RT Systems & Applications to Control System Design
Wed, May 29, 2013 @ 11:30am EDT
Levine Hall - Room 307
3330 Walnut Street
Philadelphia, PA 19104
Speaker
Nathan Fisher, Ph.D.
Wayne State University
Abstract

The recent focus upon compositional design in real-time systems research has yielded a number of promising frameworks for the integration of multiple safety- and time-critical components upon a shared computational platform.  Integration of components has a profound impact upon the size and cost of the system by potentially reducing the hardware resources that must be dedicated to ensure the safe functioning of the system.  These frameworks have also introduced many interesting open research challenges such as: 1) Allocation: how do we determine the optimal interface which accurately describes the temporal requirements of a component; 2) Isolation: how can components be isolated from the temporal faults or misbehavior of other components; 3) Dynamic Behavior: how do components adaptively change their behavior in response to a dynamic environment.

In this talk, I describe our recent work on the above challenges via the development of efficient schedulability analysis that provides formal guarantees on the temporal correctness of compositional real-time systems.  Furthermore, each of our solutions is either provably optimal or has bounded deviation from the optimal solution.  The existence of such optimality guarantees imply our solutions may be leveraged in reducing the size, weight, and power (SWaP) requirements of safety-critical real-time systems that employ component-based design.  Finally, I will discuss some surprising applications of our obtained solutions to the area of thermal-aware real-time control system design.

Speaker Bio

Nathan Fisher is an Assistant Professor in the Department of Computer Science at Wayne State University.  He received his Ph.D. from the University of North Carolina at Chapel Hill in 2007, his M.S. degree from Columbia University in 2002, and his B.S. degree from the University of Minnesota in 1999, all in computer science.   His research interests are in real-time and embedded computer systems, sustainable computing, resource allocation, game-theory, and approximation algorithms.  His current funded research projects are on composability of real-time applications, multiprocessor real-time scheduling theory, thermal-aware real-time system design, and algorithmic mechanism design in competitive real-time systems.  He received the NSF CAREER Award in 2010 and best paper awards from publication venues such as RTSS, ECRTS, and IEEE Transactions on Industrial Informatics.