EmuEdge: A Hybrid Emulator for Reproducible and Realistic Edge Computing Experiments
Additional Document Info
Numerous recent research efforts have been devoted to edge computing due to its key role in enabling emerging IoT applications. Prior to deploying edge technologies to real world environments, they need to be adequately tested, validated and tuned on a testing platform. However, to the best of our knowledge, a testing platform for edge computing that provides both networking and computing realism with low costs is still missing. In this thesis, we propose EmuEdge, a hybrid emulator based on Xen and Linuxs netns for full-stack edge computing emulation. Supporting both containers and VMs, EmuEdge is the first that takes advantage of both OS-level and full system virtualization in edge computing emulation. The hybrid design of EmuEdge ensures on-demand isolations on both computation and networking while maintaining the flexibility of scaling with lightweight containers. Besides, our system supports real-world network replay and is fully configurable with EmuEdge APIs. Through extensive experiments, we prove that EmuEdge provides realistic computation isolation and network fidelity comparing to state-of-the-art emulators. We also demonstrate EmuEdges compatibility with an actual edge computing platform and the emulation results are qualitatively similar to physical experiments.
name of conference
2019 IEEE International Conference on Fog Computing (ICFC)