AF: Small: Collaborative Research: Online Scheduling Algorithms for Networked Systems and Applications

互联网现在是世界上占主导地位的信息基础设施。来自互联网用户及其应用程序的大量请求以多种方式争夺共享资源。因此，有效分配有限的网络资源以提供高质量的服务是至关重要的。以这种方式改善互联网的性能有可能产生极其广泛的影响。当考虑到连接到互联网的移动设备时，资源管理变得更加具有挑战性。设计高效算法的难点主要在于：(1)资源请求的多样性和不可预测性；(2)网络链路、网络交换机缓冲空间、无线信道容量和移动设备电池电量的物理限制。该项目旨在为网络系统和应用中的几个基本算法问题提供解决方案。将为网络交换机转发优先数据包和移动设备的能量管理开发鲁棒且富有洞察力的在线算法。目标是了解这些问题的数学结构，设计优雅且易于实现的在线算法，对其性能边界提供严格的分析，并将这些算法集成到实际系统中以获得更好的性能。

The Internet is now the world's dominant information infrastructure. Numerous requests from Internet users and their applications compete for shared resources in multiple ways. It is therefore critical to efficiently allocate limited network resources in order to provide high quality services. Improving the performance of the Internet in this manner has the potential to have extremely broad impact. Resource management becomes even more challenging when mobile devices connecting to the Internet are considered. Designing efficient algorithms is difficult mainly due to the following factors: (1) diverse and unpredictable resource requests; (2) physical limitations on Internet links, on buffer space in network switches, on capacity of wireless channels, and on battery power in mobile devices. This project aims to provide solutions for several fundamental algorithmic problems in networked systems and applications. Robust and insightful online algorithms will be developed for network switches forwarding prioritized packets and energy management in mobile devices. The objective is to understand the mathematical structure of these problems, to design elegant and easy-to implement online algorithms, to provide rigorous analysis on their performance bounds, and to integrate these algorithms into the real systems to achieve better performance.