透過您的圖書館登入
IP:18.216.83.240
  • 期刊

一個新的適用於可強奪式固定優先權即時嵌入式系統的動態電壓調整演算法

A Novel DVS Algorithm for Preemption Fixed-Priority Hard Real-Time Embedded System

摘要


動態電壓調整是一種能有效降低微處理器消耗能量的技術,在可攜嵌入式系統技術中,如何有效地降低能量消耗尤為重要。當系統工作量較低時,動態電壓調整技術利用降低微處理器的工作電壓,使得消耗功率與能量能夠大幅地降低。在即時系統中,使用動態電壓調整技術可能會面臨時間限制的問題,因此,如何在即時系統中降低微處理器工作電壓以達到高能量效率,是一項研究議題。本文中,我們提出了一個新的DVS演算法,能夠有效地應用在可搶奪式固定優先權系統中;此演算法分為靜態部分和動態兩部分。在靜態演算法中,我們提出一個具有最佳能量效率的技術讓所有工作能夠在它的期限前完成,並且具有最小的能量消耗。在動態演算法部分,我們以一個具有精確估測鬆弛時間能力的動態演算法(lpWDA)為基礎,結合我們提出的靜態演算法,使其具有更佳的效能。經由模擬結果顯示,我們所提出的新的動態電壓調整演算法在最佳情況下,能量消耗可以減少達40%以上。

並列摘要


Dynamic voltage scaling (DVS) is one of technologies to effectively reduce energy consumption of microprocessors. In portable embedded-systems, to reduce its power consumption is an important technique. When the system workload is light, DVS strategy can lower its working voltage to significantly reduce the power/energy consumption. In real-time systems, DVS technique has the timing-constraint problem. Therefore, to lower the working voltage, which can reach the high energy efficiency, becomes a study topic. In this paper, our proposed DVS algorithm can be applied to fixed-priority preemption real-time embedded systems. Our algorithm includes the off-line and on-line phases. In off-line phase, our proposed method is the optimum energy efficiency and all tasks can complete the constraint of deadline. In on-line phase, based on a on-line algorithm for precisely estimating the slack time, our off-line algorithm can combine it and then make the better efficiency. From our simulation results, we know that the proposed algorithm can reduce the energy consumption by 40% than lpWDA.

被引用紀錄


洪志銘(2008)。具有彈性的自動化嵌入式系統功率測量平台之設計與實作〔碩士論文,國立臺北科技大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0006-2003200815171700

延伸閱讀