Sciweavers

Share
CODES
2004
IEEE

CPU scheduling for statistically-assured real-time performance and improved energy efficiency

9 years 2 months ago
CPU scheduling for statistically-assured real-time performance and improved energy efficiency
We present a CPU scheduling algorithm, called Energy-efficient Utility Accrual Algorithm (or EUA), for battery-powered, embedded real-time systems. We consider an embedded software application model where repeatedly occurring application activities are subject to deadline constraints specified using step time/utility functions. For battery-powered embedded systems, system-level energy consumption is also a primary concern. We consider CPU scheduling that (1) provides assurances on individual and collective application timeliness behaviors and (2) maximizes system-level timeliness and energy efficiency. Since the scheduling problem is intractable, EUA heuristically computes CPU schedules with a polynomial-time cost. Several properties of EUA are analytically established, including timeliness optimality during under-load situations and statistical assurances on timeliness behavior. Further, our simulation results confirm EUA's superior performance. Categories and Subject Descriptor...
Haisang Wu, Binoy Ravindran, E. Douglas Jensen, Pe
Added 20 Aug 2010
Updated 20 Aug 2010
Type Conference
Year 2004
Where CODES
Authors Haisang Wu, Binoy Ravindran, E. Douglas Jensen, Peng Li
Comments (0)
books