Energy-Aware Real-Time Task Scheduling Exploiting Temporal Locality

Yong-Hee KIM  Myoung-Jo JUNG  Cheol-Hoon LEE  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E93-D   No.5   pp.1147-1153
Publication Date: 2010/05/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E93.D.1147
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Software Systems
Keyword: 
dynamic voltage scaling,  low-power,  real-time scheduling,  temporal locality,  

Full Text: PDF>>
Buy this Article




Summary: 
We propose a dynamic voltage scaling algorithm to exploit the temporal locality called TLDVS (Temporal Locality DVS) that can achieve significant energy savings while simultaneously preserving timeliness guarantees made by real-time scheduling. Traditionally hard real-time scheduling algorithms assume that the actual computation requirement of tasks would be varied continuously from time to time, but most real-time tasks have a limited number of operational modes changing with temporal locality. Such temporal locality can be exploited for energy savings by scaling down the operating frequency and the supply voltage accordingly. The proposed algorithm does not assume task periodicity, and requires only previous execution time among a priori information on the task set to schedule. Simulation results show that TLDVS achieves up to 25% energy savings compared with OLDVS, and up to 42% over the non-DVS scheduling.