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

点击翻译按钮获取中文摘要

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.