Dynamic voltage and frequency scaling for optimal real-time scheduling on multiprocessors

Not only system performance but also energy efficiency is critically important for embedded systems. Optimal real-time scheduling is effective to not only schedulability improvement but also energy efficiency for the systems. In this paper, real-time dynamic voltage and frequency scaling (RT DVFS) techniques based on the theoretically optimal real-time static voltage and frequency scaling (RTSVFS) techniques proposed in our previous work are presented for multiprocessor systems. Simulation results show that RT-DVFS covers up the disadvantages of RT-SVFS in the sense that RTDVFS are not practically affected by the difference among systems, whereas the energy consumption of RT-SVFS highly depends on the selectable processor frequency especially in high system utilization.

[1]  Zhiyuan Li,et al.  Energy-Aware Scheduling for Real-Time Multiprocessor Systems with Uncertain Task Execution Time , 2007, 2007 44th ACM/IEEE Design Automation Conference.

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

[3]  K.G. Shin,et al.  On-line dynamic voltage scaling for hard real-time systems using the EDF algorithm , 2004, 25th IEEE International Real-Time Systems Symposium.

[4]  Kenji Funaoka,et al.  Energy-Efficient Optimal Real-Time Scheduling on Multiprocessors , 2008, 2008 11th IEEE International Symposium on Object and Component-Oriented Real-Time Distributed Computing (ISORC).

[5]  Thomas D. Burd,et al.  Energy efficient CMOS microprocessor design , 1995, Proceedings of the Twenty-Eighth Annual Hawaii International Conference on System Sciences.

[6]  Sang Hyuk Son,et al.  The case for feedback control real-time scheduling , 1998, Proceedings of 11th Euromicro Conference on Real-Time Systems. Euromicro RTS'99.

[7]  Björn Andersson,et al.  Multiprocessor Scheduling with Few Preemptions , 2006, 12th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA'06).

[8]  Kang G. Shin,et al.  Real-time dynamic voltage scaling for low-power embedded operating systems , 2001, SOSP.

[9]  James H. Anderson,et al.  Early-release fair scheduling , 2000, Proceedings 12th Euromicro Conference on Real-Time Systems. Euromicro RTS 2000.

[10]  Tei-Wei Kuo,et al.  Allocation Cost Minimization for Periodic Hard Real-Time Tasks in Energy-Constrained DVS Systems , 2006, 2006 IEEE/ACM International Conference on Computer Aided Design.

[11]  Rami G. Melhem,et al.  Scheduling with Dynamic Voltage/Speed Adjustment Using Slack Reclamation in Multiprocessor Real-Time Systems , 2003, IEEE Trans. Parallel Distributed Syst..

[12]  Campus de Viesques,et al.  Worst-Case Utilization Bound for EDF Scheduling on Real-Time Multiprocessor Systems , 2000 .

[13]  Binoy Ravindran,et al.  An Optimal Real-Time Scheduling Algorithm for Multiprocessors , 2006, 2006 27th IEEE International Real-Time Systems Symposium (RTSS'06).

[14]  Theodore P. Baker,et al.  An analysis of EDF schedulability on a multiprocessor , 2005, IEEE Transactions on Parallel and Distributed Systems.

[15]  James H. Anderson,et al.  Adapting Pfair scheduling for symmetric multiprocessors , 2005, J. Embed. Comput..

[16]  Qi Yang,et al.  Energy-aware partitioning for multiprocessor real-time systems , 2003, Proceedings International Parallel and Distributed Processing Symposium.