Generalized Network Flow Techniques for Dynamic Voltage Scaling in Hard Real-Time Systems

Authors:
Vishnu Swaminathan;Krishnendu Chakrabarty
Affiliations:
Duke University, Durham, NC;Duke University, Durham, NC
Venue:
Proceedings of the 2003 IEEE/ACM international conference on Computer-aided design
Year:
2003

Citing 6
Cited 1

Network flows: theory, algorithms, and applications

Network flows: theory, algorithms, and applications
Power conscious fixed priority scheduling for hard real-time systems

Proceedings of the 36th annual ACM/IEEE Design Automation Conference
Energy efficient fixed-priority scheduling for real-time systems on variable voltage processors

Proceedings of the 38th annual Design Automation Conference
Optimal voltage allocation techniques for dynamically variable voltage processors

Proceedings of the 40th annual Design Automation Conference
A scheduling model for reduced CPU energy

FOCS '95 Proceedings of the 36th Annual Symposium on Foundations of Computer Science
Visual assessment of a real-time system design: a case study on a CNC controller

RTSS '96 Proceedings of the 17th IEEE Real-Time Systems Symposium

Approximation algorithms for power minimization of earliest deadline first and rate monotonic schedules

ISLPED '07 Proceedings of the 2007 international symposium on Low power electronics and design

Quantified Score

Hi-index	0.00

Visualization

Abstract

Energy consumption is an important performance parameter forportable and wireless embedded systems. However, energy consumptionmust be carefully balanced with real-time responsivenessin hard real-time systems. We present an optimal offline dynamicvoltage scaling (DVS) scheme for dynamic power management insuch systems. A generalized network flow model for the uniprocessorDVS problem is developed and solved optimally using an efficientnetwork flow algorithm. The proposed method outperformsexisting DVS schemes for several popular embedded processorswhere the number of processor speeds is limited to a few values.The GNF model provides theoretical lower bounds on energy consumptionusing DVS in hard real-time systems.