The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Dynamic Voltage Scaling (DVS) é uma técnica de projeto de baixo consumo de energia bem conhecida, que ajusta a velocidade do clock e a tensão de alimentação dinamicamente para reduzir o consumo de energia de sistemas em tempo real. Estudos anteriores consideraram a distribuição probabilística das cargas de trabalho das tarefas para auxiliar o DVS no escalonamento de tarefas. Esses estudos usam informações de probabilidade para escalonamento de frequência intratarefa, mas não exploram suficientemente as oportunidades para a carga de trabalho do sistema economizar mais energia. Este artigo apresenta um novo algoritmo DVS para tarefas periódicas em tempo real baseado na análise da carga de trabalho do sistema para reduzir seu consumo de energia. Este algoritmo aproveita ao máximo as características de distribuição probabilística da carga de trabalho do sistema sob agendamento orientado por prioridade, como Earliest-Deadline-First (EDF). Resultados experimentais mostram que o algoritmo proposto reduz o tempo ocioso do processador e gasta mais tempo ocupado em velocidades de menor consumo de energia. A medição indica que, em comparação com os algoritmos DVS relativos, este algoritmo economiza energia em pelo menos 30%, ao mesmo tempo que oferece garantias de desempenho estatístico.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Zhe ZHANG, Xin CHEN, De-jun QIAN, Chen HU, "Dynamic Voltage Scaling for Real-Time Systems with System Workload Analysis" in IEICE TRANSACTIONS on Electronics,
vol. E93-C, no. 3, pp. 399-406, March 2010, doi: 10.1587/transele.E93.C.399.
Abstract: Dynamic Voltage Scaling (DVS) is a well-known low-power design technique, which adjusts the clock speed and supply voltage dynamically to reduce the energy consumption of real-time systems. Previous studies considered the probabilistic distribution of tasks' workloads to assist DVS in task scheduling. These studies use probability information for intra-task frequency scheduling but do not sufficiently explore the opportunities for the system workload to save more energy. This paper presents a novel DVS algorithm for periodic real-time tasks based on the analysis of the system workload to reduce its power consumption. This algorithm takes full advantage of the probabilistic distribution characteristics of the system workload under priority-driven scheduling such as Earliest-Deadline-First (EDF). Experimental results show that the proposed algorithm reduces processor idle time and spends more busy time in lower-power speeds. The measurement indicates that compared to the relative DVS algorithms, this algorithm saves energy by at least 30% while delivering statistical performance guarantees.
URL: https://global.ieice.org/en_transactions/electronics/10.1587/transele.E93.C.399/_p
Copiar
@ARTICLE{e93-c_3_399,
author={Zhe ZHANG, Xin CHEN, De-jun QIAN, Chen HU, },
journal={IEICE TRANSACTIONS on Electronics},
title={Dynamic Voltage Scaling for Real-Time Systems with System Workload Analysis},
year={2010},
volume={E93-C},
number={3},
pages={399-406},
abstract={Dynamic Voltage Scaling (DVS) is a well-known low-power design technique, which adjusts the clock speed and supply voltage dynamically to reduce the energy consumption of real-time systems. Previous studies considered the probabilistic distribution of tasks' workloads to assist DVS in task scheduling. These studies use probability information for intra-task frequency scheduling but do not sufficiently explore the opportunities for the system workload to save more energy. This paper presents a novel DVS algorithm for periodic real-time tasks based on the analysis of the system workload to reduce its power consumption. This algorithm takes full advantage of the probabilistic distribution characteristics of the system workload under priority-driven scheduling such as Earliest-Deadline-First (EDF). Experimental results show that the proposed algorithm reduces processor idle time and spends more busy time in lower-power speeds. The measurement indicates that compared to the relative DVS algorithms, this algorithm saves energy by at least 30% while delivering statistical performance guarantees.},
keywords={},
doi={10.1587/transele.E93.C.399},
ISSN={1745-1353},
month={March},}
Copiar
TY - JOUR
TI - Dynamic Voltage Scaling for Real-Time Systems with System Workload Analysis
T2 - IEICE TRANSACTIONS on Electronics
SP - 399
EP - 406
AU - Zhe ZHANG
AU - Xin CHEN
AU - De-jun QIAN
AU - Chen HU
PY - 2010
DO - 10.1587/transele.E93.C.399
JO - IEICE TRANSACTIONS on Electronics
SN - 1745-1353
VL - E93-C
IS - 3
JA - IEICE TRANSACTIONS on Electronics
Y1 - March 2010
AB - Dynamic Voltage Scaling (DVS) is a well-known low-power design technique, which adjusts the clock speed and supply voltage dynamically to reduce the energy consumption of real-time systems. Previous studies considered the probabilistic distribution of tasks' workloads to assist DVS in task scheduling. These studies use probability information for intra-task frequency scheduling but do not sufficiently explore the opportunities for the system workload to save more energy. This paper presents a novel DVS algorithm for periodic real-time tasks based on the analysis of the system workload to reduce its power consumption. This algorithm takes full advantage of the probabilistic distribution characteristics of the system workload under priority-driven scheduling such as Earliest-Deadline-First (EDF). Experimental results show that the proposed algorithm reduces processor idle time and spends more busy time in lower-power speeds. The measurement indicates that compared to the relative DVS algorithms, this algorithm saves energy by at least 30% while delivering statistical performance guarantees.
ER -