ZETA: Zero energy timing algebra for power aware embedded computing

This paper deals with the ZETA framework capabilities to optimize the energy requirements of real-time embedded systems. Since the system's functionality is partitioned into tasks, the embedded computer becomes power aware via power aware tasks. Each task has an individual execution rate. Tasks are clustered on the base of a common clock rate to decline the speed switching overhead.

[1]  Rami G. Melhem,et al.  On the Interplay of Parallelization, Program Performance, and Energy Consumption , 2010, IEEE Transactions on Parallel and Distributed Systems.

[2]  Massoud Pedram,et al.  Dynamic voltage and frequency scaling under a precise energy model considering variable and fixed components of the system power dissipation , 2004, IEEE/ACM International Conference on Computer Aided Design, 2004. ICCAD-2004..

[3]  Giuseppe Lipari,et al.  Speed modulation in energy-aware real-time systems , 2005, 17th Euromicro Conference on Real-Time Systems (ECRTS'05).

[4]  Ragunathan Rajkumar,et al.  Critical power slope: understanding the runtime effects of frequency scaling , 2002, ICS '02.

[5]  Yu Guo,et al.  Parallel Embedded Systems: Where Real-Time and Low-Power Meet , 2008, PDCCS.

[6]  Rami Melhem,et al.  Power management points in power-aware real-time systems , 2002 .

[7]  Emil Vassev,et al.  Energy Efficiency with Runtime Models for Energy-aware Embedded Systems , 2011, 2011 IEEE 34th Software Engineering Workshop.

[8]  Petru Eles,et al.  System-Level Design Techniques for Energy-Efficient Embedded Systems , 2003, Springer US.

[9]  Z. Karakehayov.  Dynamic Clock Scaling for Energy-aware Embedded Systems , 2007, 2007 4th IEEE Workshop on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications.