Allocation CostMinimization forPeriodic HardReal-Time TasksinEnergy-Constrained DVSSystems*

Energy-efficiency andpower-awareness forelectronic systems have beenimportant design issues inhardware andsoftware implementations. We consider thescheduling ofperiodic hardreal-time tasks along withtheallocation ofprocessors under agiven energy constraint. Eachprocessor typecould beassociated withitsallocation cost. Theobjective ofthis workistominimize theentire allocation costofprocessors sothat thetiming andenergy constraints areboth satisfied. Wedevelop approximation algorithms forprocessor types withcontinuous processor speeds ordiscrete processor speeds. The capability oftheproposed algorithms wasevaluated byaseries of experiments, anditwasshownthat theproposed algorithms always derived solutions withsystem costs close tothose ofoptimal solutions intheexperiments.

[1]  Chung Laung Liu,et al.  Scheduling Algorithms for Multiprogramming in a Hard-Real-Time Environment , 1989, JACM.

[2]  Rami G. Melhem,et al.  Multiversion scheduling in rechargeable energy-aware real-time systems , 2003, 15th Euromicro Conference on Real-Time Systems, 2003. Proceedings..

[3]  Vijay V. Vazirani,et al.  Approximation Algorithms , 2001, Springer Berlin Heidelberg.

[4]  Hakan Aydin,et al.  Energy-constrained scheduling for weakly-hard real-time systems , 2005, 26th IEEE International Real-Time Systems Symposium (RTSS'05).

[5]  Jan M. Rabaey,et al.  Digital Integrated Circuits , 2003 .