Michigan Researchers Win Best Poster Award at MobiSys 2015

It describes their work in measuring important network phenomena for debugging problems at the edge of a cellular network.

Image Enlarge
Michigan researchers Shichang Xu and Ashkan Nikravesh

Computer science and engineering researchers won the best poster award at the 13th International Conference on Mobile Systems, Applications, and Services (MobiSys 2015), which took place May 18-22 in Florence, Italy.

The poster, entitled “Context-Triggered Mobile Network Measurement,” was created by Shichang Xu, Ashkan Nikravesh, Hongyi Yao (University of Michigan), David R. Choffnes (Northwestern University) with advisor Prof. Z. Morley Mao. It describes their work in measuring important network phenomena for debugging problems at the edge of a cellular network.

The researchers note that to diagnose and debug network problems in a cellular network, network measurements from mobile devices are needed. However, network and battery resources to conduct measurements from mobile devices are scarce and traditional network measurement approaches that use continuous, periodic or random measurements are either infeasible or ineffective in this environment.

In their work, they propose triggering measurements based on relevant device context such as signal strength and historical performance data etc. By carefully selecting when to conduct a measurement and using prediction to improve the likelihood that triggered measurements will succeed, they can more reliably measure important network phenomena with less overhead.

Using Mobilyzer as a platform for evaluation, they propose an architecture that is sufficiently general to support a wide range of triggered measurement experiments. They demonstrate the use of this framework for measurements on mobile platforms that are traditionally difficult to capture, e.g., handoff measurement. Furthermore, they can use the global scheduler to predict which devices will likely satisfy the preconditions for the triggered measurement to improve the measurement success rate.