Task Migration for Energy Conservation in Real-Time Multi-processor Embedded Systems

In recent years, portable devices and tablet PCs grow fast and become more convenient and mobile. Applications like multimedia, SIP, and 3D movies become more diverse than before. However, the complex architecture and heavy computing demands increase energy consumption. Therefore, how to extend the standby and usage time of the devices has become an important issue. In this paper we propose a task scheduling algorithm in a real-time multi-processor system. We reduce the workload in high speed processors with the aid of task migration so that the entire system can switch to low speed as soon as it can in order to reduce energy consumption. A distinctive feature is that actual execution time is used in the decision instead of worst-case execution time, which allows for more effective task migration. Performance results based on realistic processor power consumption models are promising. Effects of parameter values on the performance are also examined.

[1]  Rami G. Melhem,et al.  Energy-efficient policies for request-driven soft real-time systems , 2004, Proceedings. 16th Euromicro Conference on Real-Time Systems, 2004. ECRTS 2004..

[2]  R. Kumar,et al.  An Integrated Quad-Core Opteron Processor , 2007, 2007 IEEE International Solid-State Circuits Conference. Digest of Technical Papers.

[3]  Jan M. Rabaey,et al.  Power Sources for Wireless Sensor Networks , 2004, EWSN.

[4]  Krishna V. Palem,et al.  The emerging power crisis in embedded processors: what can a poor compiler do? , 2001, CASES '01.

[5]  Lizy K. John,et al.  Is Compiling for Performance — Compiling for Power? , 2001 .

[6]  Abhijit S. Pandya,et al.  Power Management System for Embedded RTOS: An Object Oriented Approach , 2006, 2006 Canadian Conference on Electrical and Computer Engineering.

[7]  Trevor N. Mudge,et al.  Power: A First-Class Architectural Design Constraint , 2001, Computer.

[8]  Zhao Lei,et al.  A dynamic frequency scaling solution to DPM in embedded Linux systems , 2009, 2009 IEEE International Conference on Information Reuse & Integration.

[9]  Andrew Wolfe,et al.  Compilation techniques for low energy: an overview , 1994, Proceedings of 1994 IEEE Symposium on Low Power Electronics.

[10]  Rami G. Melhem,et al.  Practical PACE for embedded systems , 2004, EMSOFT '04.

[11]  John P. Lehoczky,et al.  Algorithms for scheduling hard aperiodic tasks in fixed-priority systems using slack stealing , 1994, 1994 Proceedings Real-Time Systems Symposium.

[12]  Mani B. Srivastava,et al.  Design considerations for solar energy harvesting wireless embedded systems , 2005, IPSN 2005. Fourth International Symposium on Information Processing in Sensor Networks, 2005..

[13]  Yuhua Zhang,et al.  A Practical Dynamic Frequency Scaling Solution to DPM in Embedded Linux Systems , 2009, J. Comput..

[14]  Fernando Gehm Moraes,et al.  Evaluating the impact of task migration in multi-processor systems-on-chip , 2010, SBCCI '10.

[15]  Hyejeong Hong,et al.  Total Energy Minimization of Real-Time Tasks in an On-Chip Multiprocessor Using Dynamic Voltage Scaling Efficiency Metric , 2008, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[16]  James W. Layland,et al.  Scheduling Algorithms for Multiprogramming in a Hard-Real-Time Environment , 1989, JACM.

[17]  Hiroaki Takada,et al.  Practical Energy-Aware Scheduling for Real-Time Multiprocessor Systems , 2009, 2009 15th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications.

[18]  Luca Benini,et al.  System-level power estimation and optimization , 1998, Proceedings. 1998 International Symposium on Low Power Electronics and Design (IEEE Cat. No.98TH8379).

[19]  David E. Culler,et al.  Perpetual environmentally powered sensor networks , 2005, IPSN 2005. Fourth International Symposium on Information Processing in Sensor Networks, 2005..