We propose a novel thermal-conscious power model for integrated circuits that can accurately predict power and temperature under voltage scaling. Experimental results show that the leakage power consumption is underes...We propose a novel thermal-conscious power model for integrated circuits that can accurately predict power and temperature under voltage scaling. Experimental results show that the leakage power consumption is underestimated by 52 % if thermal effects are omitted. Furthermore, an inconsistency arises when energy and temperature are simultaneously optimized by dynamic voltage scaling. Temperature is a limiting factor for future integrated circuits,and the thermal optimization approach can attain a temperature reduction of up to 12℃ with less than 1.8% energy penalty compared with the energy optimization one.展开更多
With the increasing energy consumption of computing systems and the growing advocacy for green computing, energy efficiency has become one of the critical challenges in high-performance heterogeneous computing systems...With the increasing energy consumption of computing systems and the growing advocacy for green computing, energy efficiency has become one of the critical challenges in high-performance heterogeneous computing systems. Energy consumption can be reduced by not only hardware design but also software design. In this paper, we propose an energy-aware scheduling algorithm with equalized frequency, called EASEF, for parallel applications on heterogeneous computing systems. The EASEF approach aims to minimize the finish time and overall energy consumption. First, EASEF extracts the set of paths from an application. Then, it reconstructs the application based on the extracted set of paths to achieve a reasonable schedule. Finally, it adopts a progressive way to equalize the frequency of tasks to reduce the total energy consumption of systems. Randomly generated applications and two real-world applications are examined in our experiments. Experimental results show that the EASEF algorithm outperforms two existing algorithms in terms of makespan and energy consumption.展开更多
The major aim of power quality(PQ) enhancing techniques is to maintain a specified voltage magnitude at a desired frequency for sensitive loads irrespective of faults on the power distribution network.The dynamic volt...The major aim of power quality(PQ) enhancing techniques is to maintain a specified voltage magnitude at a desired frequency for sensitive loads irrespective of faults on the power distribution network.The dynamic voltage restorer(DVR) is a device used to mitigate voltage sags to regulate load voltage.This paper presents a mathematical model for leading series voltage injection to mitigate sags thereby achieving the improvement of the utility power factor as well as power sharing between the DVR and utility.The power sharing will be as per requirement to compensate the sags considering the available distributed generation(DG).The approach of mitigating voltage sags using the concept of leading series voltage injection is suitable for those locations where phase shift in the voltage will not cause any problem.The MATLAB/SIMULINK SimPowerSystem toolbox has been used to obtain simulation results to verify the proposed mathematical model.展开更多
文摘We propose a novel thermal-conscious power model for integrated circuits that can accurately predict power and temperature under voltage scaling. Experimental results show that the leakage power consumption is underestimated by 52 % if thermal effects are omitted. Furthermore, an inconsistency arises when energy and temperature are simultaneously optimized by dynamic voltage scaling. Temperature is a limiting factor for future integrated circuits,and the thermal optimization approach can attain a temperature reduction of up to 12℃ with less than 1.8% energy penalty compared with the energy optimization one.
基金Project supported by the National Natural Science Foundation of China （Nos. 61133005, 61432005, 61370095, 61472124, and 61402400）
文摘With the increasing energy consumption of computing systems and the growing advocacy for green computing, energy efficiency has become one of the critical challenges in high-performance heterogeneous computing systems. Energy consumption can be reduced by not only hardware design but also software design. In this paper, we propose an energy-aware scheduling algorithm with equalized frequency, called EASEF, for parallel applications on heterogeneous computing systems. The EASEF approach aims to minimize the finish time and overall energy consumption. First, EASEF extracts the set of paths from an application. Then, it reconstructs the application based on the extracted set of paths to achieve a reasonable schedule. Finally, it adopts a progressive way to equalize the frequency of tasks to reduce the total energy consumption of systems. Randomly generated applications and two real-world applications are examined in our experiments. Experimental results show that the EASEF algorithm outperforms two existing algorithms in terms of makespan and energy consumption.
基金Project(No. UET/ASR&TD-251/2006)supported by the Higher Education Commission of Pakistan
文摘The major aim of power quality(PQ) enhancing techniques is to maintain a specified voltage magnitude at a desired frequency for sensitive loads irrespective of faults on the power distribution network.The dynamic voltage restorer(DVR) is a device used to mitigate voltage sags to regulate load voltage.This paper presents a mathematical model for leading series voltage injection to mitigate sags thereby achieving the improvement of the utility power factor as well as power sharing between the DVR and utility.The power sharing will be as per requirement to compensate the sags considering the available distributed generation(DG).The approach of mitigating voltage sags using the concept of leading series voltage injection is suitable for those locations where phase shift in the voltage will not cause any problem.The MATLAB/SIMULINK SimPowerSystem toolbox has been used to obtain simulation results to verify the proposed mathematical model.
