期刊名称：Journal of Emerging Trends in Computing and Information Sciences
电子版ISSN：2079-8407
出版年度：2014
卷号：4
期号：12
页码：900-907
出版社：ARPN Publishers
摘要：Cluster computing has attracted attention for large scale computing using idle CPU cycles of personal computers connected in local area network. We propose a green broker with imprecise computation scheduling for large scale computing in clusters. Imprecise computation techniques provide scheduling flexibility by trading off result quality to meet computation deadlines. We provide a technique to enhance QoS for real-time systems and improve the energy efficiency for large scale computing in clusters with lower carbon emission. Measurements of simulation on a large number of task sets show that imprecise computation improves the system reliability when scheduling intensive workloads. With less schedule faults, CPU cycles are saved and energy-efficiency is improved for large scale computing in clusters.
关键词：cluster computing; large scale computing; imprecise computation; scheduling; and energy efficiency
