Experimental Software Systems: Dynamic Resource Management for a Network-Centric Operating System

9870736Campbell, Roy H.Mickunas, Dennis m .伊利诺伊大学厄巴纳-香槟分校实验软件系统：以网络为中心的操作系统的动态资源管理该项目研究下一代以网络为中心、面向用户和面向应用的分布式系统的操作系统和资源管理问题，这些系统可以适应频繁的变化。计算和数字通信的快速发展和变化对涉及计算的科学和工程努力造成了沉重的负担。该研究建立在一个创新的服务模型之上，在这个模型中，分布式系统可以自定义以更好地满足用户和应用程序的需求。在这个模型中，用户不再是一个特定机器的本地实体——每个用户都是一个独立于机器的实体，存在于网络中，可以透明地跨不同的硬件和软件携带其配置文件。以网络为中心的操作系统管理和分配资源，以支持异构平台上的用户。资源管理包含一个架构感知框架。这构成了可适应的服务质量、动态安全性和自配置的基础。该方法支持分布式桌面、移动工作区和跨资源范围的遗留应用程序，包括使用有线和无线通信媒体的移动个人数字助理（pda）、嵌入式系统、工作站和超级计算机。简单地说，目标是通过将自适应动态和重新配置纳入分布式操作系统的资源管理机制和算法来管理与计算机技术进步相关的开销。

9870736Campbell, Roy H.Mickunas, Dennis M.University of Illinois at Urbana-ChampaignExperimental Software Systems: Dynamic Resource Management for a Network-Centric Operating SystemThis project researches the operating system and resource management concerns for next generation network-centric, user- and application-oriented distributed systems that accommodate frequent change. The rapid growth and change of computing and digital communication taxes scientific and engineering endeavors involving computation. The research builds upon an innovative service model in which the distributed system customizes itself to better the fulfillment of user and application requirements. In this model, a user is no longer an entity that is local to one specific machine -- each user is a machine-independent entity that exists in the network and can transparently carry its profile across different hardware and software. A network-centric operating system manages and allocates the resources to support the user on heterogeneous platforms. Resource management encompasses a framework for architecture-awareness. This forms the basis for adaptable quality of service, dynamic security, and self-configuration. The approach supports distributed desktops, mobile workspaces, and legacy applications across a spectrum of resources including mobile Personal Digital Assistants (PDAs), embedded systems, workstations, and supercomputers using wired and wireless communications media. Simply put, the goal is to manage the overhead associated with computer technological advances by factoring adaptive dynamics and reconfiguration into the resource management mechanisms and algorithms of distributed operating systems.