Network performance measurements are routinely collected by Internet researchers and users in order to assess whether the network is performing as expected or whether there might be some type of impairment. 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. In other words, the objective is to develop automated techniques to determine whether a given measurement is "good" or "bad".
For summer 2019, the specific goals are to deploy existing research software on Raspberry Pi (or similar) devices within the Computer Science department and to create software infrastructure for continuous measurement, data collection, and data analysis. Students will gain experience with the Linux operating system, working at a command line, collecting and understanding network performance measurements, and data collection and analysis. The project duration for summer 2019 is 8-10 weeks.
Students will need to have completed COSC 102, at minimum.