隨著科技日新月異，攜帶型消費電子產品，如：手機、PDA、…也日益普及。這些電子產品強調小巧攜帶方便，不可能設計過大的電池空間，而且電池也有一定的能源容量。所以如何降低能源消耗以延長系統運作時間就成為一門重要的議題。對這些電子產品而言，中央處理器是主要的能源消耗者。而動態電壓調整技術(Dynamic Voltage Scaling technology)動態地調整中央處理器電壓機制可以有效率地降低能源消耗。但是在這些產品內部會執行某些及時工作，不適當地降低電壓反而可能造成這些及時工作達不到及時要求。所以在此篇論文中，我們提出一個低功率及時排程演算法--LPRM(Low-Power Rate-Monotonic)。LPRM演算法不僅滿足及時工作的及時要求，而且還可以降低能源消耗。LPRM演算法是基於Rate Monotonic排程演算法衍生的低功率排程演算法。此外，LPRM演算法的運作簡單，僅需花費 O(n) 和 O(1) 時間複雜度在靜態和動態狀態下。因為LPRM有上述特性又不複雜，所以可以輕易地實作在現有的作業系統內。從實驗數據中得知，LPRM可節省25% ~ 35%的能源，而LPRM的進階延伸版本可以節省30% ~ 45%的能源。

Energy consumption has become a critical issue for a portable and wireless embedded device because of its limited energy capacity of batteries. An application that runs on such a system often imposes real-time constraints that a task must complete its execution before its deadline. In this paper, we propose a low-power real-time scheduling algorithm called LPRM for fixed-priority periodic scheduling. LPRM, based on the technique of dynamic Voltage Scaling, is a low-power extension of the Rate-Monotonic algorithm. Due to its simplicity and low complexity, LPRM can be easily implemented in a power-aware real-time embedded system for energy reduction. To demonstrate its performance impact, we conduct a set of experiments to compare energy reduction of LPRM with other approaches. The experimental results show that LPRM, with a simple extension, achieves better energy reduction. Particularly, compared with the static speed approach, LPRM reduces energy consumption by 45% for a set of 25 tasks with variable execution times.

[1] Hakan Aydin, Rami Melhem, Daniel Moss´e, and Pedro Mej´ıa-Alvarez. Optimal reward-based scheduling of periodic real-time tasks. In IEEE Real-Time Systems Symposium, pages 79–89, 1999.
[2] Hakan Aydin, Rami Melhem, Daniel Moss´e, and Pedro Mej´ıa-Alvarez. Determining optimal processor speeds for periodic realtime tasks with different power characteristics. In Euromicro Conference on Real-Time Systems, pages 225–232, 2001.
[3] Hakan Aydin, Rami Melhem, Daniel Moss´e, and Pedro Mej´ıa-Alvarez. Dynamic and aggressive scheduling techniques for poweraware real-time systems. In IEEE Real-Time Systems Symposium, pages 95–105, 2001.
[4] Enrico Bini, Giorgio C. Buttazzo, and Giuseppe M. Butazzo. Rate monotonic analysis: The hyperbolic bound. 52:933–942, 2003.
[5] eCos. http://www.ecoscentric.com/.
[6] Flavius Gruian. Hard real-time scheduling for low-energy using stochastic data and DVS processors. In International Symposium on Low Power Electronics and Design, pages 46–51, 2001.
[7] Inki Hong, Miodrag Potkonjak, and Mani B. Srivastava. On-line scheduling of hard real-time tasks on variable voltage processor. In International Conference on Computer-Aided Design, pages 653–656, 1998.
[8] John Lehoczky, Lui Sha, and Ye Ding. The rate monotonic
scheduling algorithm: Exact characterization and average case behavior. In IEEE Real-Time Systems Symposium, pages 166–171, 1989.
[9] C. L. Liu and James W. Layland. Scheduling algorithms for multiprogramming in a hard real-time environment. Journal of the ACM, 20(1):46–61, 1973.
[10] Jane W.S. Liu. Real-Time Systems. Prentice Hall, 2000.
[11] µC/OS II. http://www.micrium.com/.
[12] Padmanabhan Pillai and Kang G. Shin. Real-time dynamic voltage scaling for low-power embedded operating systems. In ACM Symposium on Operating Systems Principles, pages 89–102, 2001.
[13] Gang Quan and Xiaobo (Sharon) Hu. Energy efficient fixed-priority scheduling for real-time systems on variable voltage processors. In Annual ACM IEEE Design Automation Conference, pages 828–833, 2001.
[14] Gang Quan and Xiaobo Sharon Hu. Minimum energy fixed-priority scheduling for variable voltage processors. In Design, Automation, and Test in Europe, pages 782–787, 2002.
[15] RTLinux. http://www.fsmlabs.com/.
[16] Youngsoo Shin and Kiyoung Choi. Power conscious fixed priority scheduling for hard real-time systems. In Annual ACM IEEE Design Automation Conference, pages 134–139, 1999.
[17] Youngsoo Shin, Kiyoung Choi, and Takayasu Sakurai. Power optimization of real-time embedded systems on variable speed processors. In International Conference on Computer Aided Design, pages 365–368, 2000.
[18] Frances Yao, Alan Demers, and Scott Shenker. A scheduling model for reduced cpu energy. In IEEE Annual Foundations of Computer Science, pages 374–382, 1995.
[19] Han-Saem Yun and Jihong Kim. On energy-optimal voltage
scheduling for fixed-priority hard real-time systems. ACM Transactions on Embedded Computing Systems, 2:393–430, 2003.
[20] Fan Zhang and Samuel T. Chanson. Processor voltage scheduling for real-time tasks with non-preemptible sections. In IEEE Real-Time Systems Symposium, pages 235–245, 2002.