Feedback Control Real-Time Scheduling: Framework, Modeling, and Algorithms
Abstract
This paper presents a Feedback Control real-time Scheduling (FCS) framework for adaptive realtime systems. An advantage of the FCS framework is its use of feedback control theory (rather than ad hoc solutions) as a scientific underpinning. We apply a control theory based methodology to systematically design FCS algorithms to satisfy the transient and steady state performance specifications of real-time systems. In particular, we establish dynamic models of real-time systems and develop performance analyses of FCS algorithms, which are major challenges and key steps for the design of control theory based adaptive real-time systems. We also present a FCS architecture that allows plug-ins of different real-time scheduling policies and QoS optimization algorithms. Based on our framework, we identify different categories of real-time applications where different FCS algorithms should be applied. Performance evaluation results demonstrate that our analytically tuned FCS algorithms provide robust transient and steady state performance guarantees for periodic and aperiodic tasks even when the task execution times vary by as much as 100% from the initial estimate.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2006
- Accession Number
- ADA446903
Entities
People
- Chenyang Lu
- Gang Tao
- John A. Stankovic
- Sang H. Son
Organizations
- University of Virginia