NeTS: Small: RUI: Automating Active Measurement Metadata Collection and Analysis

点击翻译按钮获取中文摘要

The extraordinary growth of Internet connectivity and bandwidth has helped to fuel economic activity, educational opportunities, and social connections around the world. The network research community has continued to play a critical role in assessing current Internet performance and in using measurements of network performance and behavior toward the design of new and improved infrastructure, protocols, and applications. Even with advances in network performance measurement techniques over the years, however, it is easily possible for measurements to exhibit bias or otherwise be error-ridden. The primary objective of this project is to develop methods for capturing important contextual information about a network performance measurement experiment and to create algorithms to assess whether the measurements exhibit bias or other problems. Extensive experiments will be carried out in both a campus network and in the wide-area Internet to evaluate the tools developed through this project. The outcomes of this project will potentially improve the quality and reproducibility of performance measurements produced through efforts such as the Federal Communication Committee?s (FCC's) Measuring Broadband America as well as other prominent network measurement efforts. Empirical research in the Internet is fraught with challenges. Perhaps chief among these is that local environmental conditions (e.g., central processing unit (CPU) load or network load) can introduce unexpected bias or artifacts that can lead to poor measurement quality and erroneous conclusions. This project will investigate and develop new methods for automatic collection of metadata and calibration data for network measurement experiments and create algorithms for detecting and potentially correcting for bias in the measurement data. Collection of metadata for measurement methods that target all layers of the protocol stack will be addressed through this project, such as latency (ping), routing (traceroute), TCP throughput, and application-level performance measurements. The tools developed through this project will be deployed for extensive experimentation in a campus network as well in a widely-used platform to evaluate and improve their performance and operational capabilities. The tools will be made openly available to the research community and will be designed for lightweight operation on a variety of target computing platforms and thus be broadly deployable. Best-practices documentation will be created and published to facilitate optimal use of the tools and algorithms developed through our research. The methods, algorithms, and software developed through this project will provide Internet measurement researchers with a toolbox for collecting and analyzing metadata and the associated data from experiments. These techniques will potentially improve confidence in the use of network measurement data not only by the researcher who captures the data, but by others who may eventually use the data. They will also enhance scientific reproducibility by providing portable, independent, and scalable methods to capture important contextual information about experiments. The tools and methods developed through this project will potentially improve the quality of measurements and outcomes produced through efforts such as the FCC's Measuring Broadband America, which directly serves the national interest through the progress of science. Lastly, undergraduate students will be involved in all stages of the research, providing them with invaluable extracurricular experiences, and inspiring them to pursue careers in science and engineering, a goal which also serves the national interest.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.