Maximizing the system value while satisfying time and energy constraints
Autor: | Cosmin Rusu, Daniel Mosse, Rami Melhem |
---|---|
Rok vydání: | 2003 |
Předmět: |
Scheme (programming language)
Mathematical optimization Computational complexity theory General Computer Science Energy management Computer science Distributed computing Quality of service Value (computer science) Admission control Energy consumption Task (project management) Variety (cybernetics) Control system Fraction (mathematics) Energy source Computer Science::Operating Systems computer Energy (signal processing) computer.programming_language |
Zdroj: | RTSS |
ISSN: | 0018-8646 |
DOI: | 10.1147/rd.475.0689 |
Popis: | Typical real-time scheduling theory has addressed deadline and energy constraints as well as deadline and reward constraints simultaneously in the past. However we believe that embedded devices with varying applications typically have three constraints that need to be addressed: energy, deadline, and reward. These constraints play important roles in the next generation of embedded devices, since they provide users with a variety of QoS-aware trade-offs. An optimal scheme would allow the device to run the most critical and valuable applications, without depleting the energy source while still meeting all deadlines. In this paper we propose a solution to this problem for typical control systems, such as frame-based task sets. We devise two algorithms that closely approximate the optimal solution while taking only a fraction of the runtime of an optimal solution. |
Databáze: | OpenAIRE |
Externí odkaz: |