Many emerging mobile applications, including augmented reality (AR) and  wearable cognitive assistance (WCA), aim to provide seamless user  interaction. However, the complexity of benchmarking these  human-in-the-loop applications limits reproducibility and makes  performance evaluation difficult. In this paper, we present EdgeDroid, a  benchmarking suite designed to reproducibly evaluate these  applications. Our core idea rests on recording traces of user  interaction, which are then replayed at benchmarking time in a  controlled fashion based on an underlying model of human behavior. This  allows for an automated system that greatly simplifies benchmarking  large scale scenarios and stress testing the application. Our results  show the benefits of EdgeDroid as a tool for both system designers and  application developers.

Olguín, M., Wang, J., Satyanarayanan, M., Gross, J.
Proceedings of the 20th International Workshop on Mobile Computing Systems and Applications (HotMobile ’19), Santa Cruz, CA, February 2019