Managing Energy as a First Class Operating System Resource

将能源作为一流的操作系统资源进行管理

• 批准号: 0204367
• 负责人: Carla Ellis
• 金额: $ 25万
• 依托单位: Duke University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2002
• 资助国家: 美国
• 起止时间: 2002-06-01 至 2005-05-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0204367&HistoricalAwards=false
• 关键词: Managing; Energy; First; Class; Operating

Managing the energy consumption of computers requires cooperationbetween energy aware applications and operating systems. Thisresearch seeks to fully explore the energy management spacesurrounding the interaction of applications and the operating system.Applications should adjust their energy consumption when appropriate,but must be provided accurate information on their individual energyconsumption. The operating system must implement the mechanisms andpolicies to determine energy consumption and allocate it fairly as aglobal system resource.This research will first re-examine operating system structure with anemphasis on managing energy as a first class resource. Energymanagement cuts across all traditional system resources, with the CPU,disk, network, and memory all exhibiting unique energy consumptioncharacteristics. Next, the work will explore policies for allocatingenergy to competing tasks. The goal is to maintain fairness whileobserving user-specified priorities and soft real-time deadlines.The end product of this research will be a comprehensive framework forglobally managing energy in a diverse set of scenarios, ranging from asingle mobile computer, to wireless sensor networks that may haveaggregate goals across a large number of sensors, to hosting centersthat wish to provide maximum performance with minimum energyconsumption.

管理计算机的能源消耗需要能源感知应用程序和操作系统之间的合作。 本研究旨在充分探索围绕应用程序和操作系统交互的能源管理空间，应用程序应在适当的时候调整其能源消耗，但必须提供有关其个体能源消耗的准确信息。 操作系统必须执行机制和策略来确定能量消耗并将其公平地分配为一级系统资源。本研究将首先重新审视操作系统结构，重点是将能量作为一级资源进行管理。 能源管理跨越所有传统的系统资源，CPU、磁盘、网络和内存都表现出独特的能耗特征。 下一步，这项工作将探索将能源分配给竞争任务的政策。 我们的目标是在遵守用户指定的优先级和软实时截止日期的同时保持公平性。这项研究的最终产品将是一个全面的框架，用于在各种场景中进行全球能源管理，从单个移动的计算机到可能在大量传感器上具有聚合目标的无线传感器网络，再到希望以最小能耗提供最大性能的托管中心。