CISE Experimental Partnerships: Processing/Communication/ Interface Tradeoffs to Optimize Energy Locality in Mobile Systems

99- 01321 Siewiorek，DanielKoopman，PhilipCarnegie Mellon UniversityCISE实验合作伙伴关系：处理/通信/接口权衡优化移动的系统中的能源局部性随着计算机的不断缩小，对移动的/可穿戴计算的研究和商业兴趣正在迅速增长。 与传统的桌面计算需要用户来到计算机前不同，移动的计算将计算机带到用户面前。 移动的/可穿戴计算的关键问题之一是能耗。 移动的/可穿戴计算机的电池重量通常超过所有其他组件的组合重量。 为了使移动的/可穿戴计算广泛适用，需要在降低功耗和电池重量方面取得重大进展。 在这项研究中，Infocator，正在开发中的移动的/可穿戴计算的能量问题进行研究。移动的/可穿戴系统通常由计算和通信系统。 虽然计算组件所需的功耗正在快速降低，但通信组件所需的功耗没有跟上。 据估计，到2001年，移动的/可穿戴设备所消耗的功率中有近80%将来自于通信，通过有效地划分控制和数据，将高能耗的通信转换为低能耗的计算，可以显著地节省能源。 用于确定理想的控制/数据分割的方法正在开发中，并编入能量局部性理论。 为了实现分区和方便控制移动，一个通用的应用程序独立的代理框架也正在开发中。 为了最大限度地提高可穿戴系统在移动的计算环境中的效率，界面设计必须与用户任务仔细匹配，并与能耗进行平衡。 许多复杂且相互关联的问题决定了易用性和功耗之间的平衡。 简单地将易用性与较低的每次操作功耗进行权衡可能会导致更高的任务能耗，因为遍历不太直观的界面所需的操作数量增加。 用户界面对能耗的影响也正在通过为nfocator开发几种不同的界面并测量和比较易用性和能耗来评估。

99-01321Siewiorek, DanielKoopman, PhilipCarnegie Mellon UniversityCISE Experimental Partnerships: Processing/Communication/InterfaceTradeoffs to Optimize Energy Locality in Mobile SystemsAs computers continue to shrink, research and commercial interest in mobile/wearable computing is rapidly growing. Unlike traditional desktop computing in which the user is required to come to the computer, mobile computing brings the computer to the user. One of the key problems with mobile/wearable computing is energy consumption. Battery weight for mobile/wearable computers often exceeds the weight of all other components combined. In order to make mobile/wearable computing widely applicable, major advances in reducing power consumption and battery weight are needed. In this research a testbed, Infocator, is being developed to study energy issues in mobile/wearable computing.Mobile/wearable systems are typically comprised of both computing and communications systems. While power consumption required by the computing component is rapidly decreasing, power consumption required by the communications component is not keeping pace. It is estimated that by the year 2001, nearly 80% of the power consumed by mobile/wearable will be due to communications.Trading off energy-expensive communication for energy cheap computation through effective partitioning of control and data can result in significant energy savings. Methods for determining the ideal control/datapartitioning are being developed and codified in a Theory of Energy Locality. To realize the partitioning and facilitate control movement, a generic application independent framework for proxies is also beingdeveloped. To maximize the effectiveness of wearable systems in mobile computing environments, the interface design ust be carefully matched with user tasks and balanced against energy consumption. Many complex and interrelated issues determine the balance between ease-of-use and power consumption. Simply trading off ase-of-use for lower per operation power consumption may result in higher task energy consumption due to the increase in the number of operations needed to traverse a less intuitive interface. The effect of user interface on energy consumption is also being evaluated by developing several different interfaces for nfocator and measuring and comparing the ease-of-use and energy consumption.