NeTS-NBD: Toward Building a Performance-Predictable Wireless Mesh Network

迈向建立一个性能可预测的无线网状网络jennifer HouCommunity无线网络已经获得了极大的关注。尽管在几个城市范围的无线接入项目中取得了初步成功，但也发现了一些与性能相关的问题，包括过多的数据包丢失、不可预测的信道行为、无法找到稳定和高吞吐量的路由，以及由于流内和流间干扰造成的吞吐量损失。这些问题的根源都在于无线环境中不再存在链路的概念。由Jennifer Hou领导的UIUC团队采用自下而上的方法，并通过更好地定义和表征无线链路及其对高层协议设计和优化的影响来解决问题。他们希望(i)了解无线链路如何以及在多大程度上受到PHY/MAC属性和其他环境因素的影响，（ii）以一种适合严格分析的方式表征无线链路的行为，以及（iii）确定MAC/PHY层中的控制旋钮，通过这些旋钮可以优化网络容量。为了对测量、表征和设计组件进行这样的研究，UIUC团队与Champaign-Urbana Wireless Mesh Network （CUWiN）合作，实质性地扩展其操作软件基础设施，并在固件之上放置虚拟设备驱动程序。虚拟设备驱动程序支持动态调整控制旋钮以提高网络容量，并通过定义良好的api导出PHY/MAC属性，以促进跨层设计和优化。该项目的预期结果是（基于实际测量）在严格的分析基础上理解影响无线链路、控制旋钮及其相应控制机制行为的因素，并通过在CUWiN上的软件系统构建和实验对其进行验证和评估。

Toward Building a Performance-Predictable Wireless Mesh NetworkAward 0626584Jennifer HouCommunity wireless networks have gained tremendous attention. Although initial success has been reported in several city-wide wireless access projects, a number of performance related problems have also been identified, including excessive packet losses, unpredictable channel behaviors, inability to find stable and high-throughput routes, and throughput loss due to intra-flow and inter-flow interference. These problems are all rooted in the fact that the notion of a link no longer exists in wireless environments. The UIUC team led by Jennifer Hou takes a bottom-up approach, and tackles issues with better definition and characterization of wireless links and their implications for higher-layer protocol design and optimization. They would like to (i) understand how, and to what extent, wireless links are affected by PHY/MAC attributes and other environmental factors, (ii) characterize the behavior of wireless links in such a way that they become amenable to rigorous analysis, and (iii) identify control knobs in the MAC/PHY layers with which the network capacity can be optimized. To make such a study with measurement, characterization, design components, the UIUC team works with Champaign-Urbana Wireless Mesh Network (CUWiN) to substantially extend its operational software infrastructure, and lays a virtual device driver on top of firmware. The virtual device driver enables dynamic tuning of control knobs to improve network capacity, and exports PHY/MAC attributes through well-defined APIs to facilitate cross-layer design and optimization. The anticipated results of this project are an understanding (based on real-life measurements) of factors that affect the behaviors of wireless links, control knobs and their corresponding control mechanisms based on a rigorous, analytical foundation, and their validation and assessment with software system building and experimentation on CUWiN.