Menes: Towards a Generic, Fully-Automated Test and Validation Platform for Wireless Networks

Abstract A major step in developing robust wireless systems is to test and validate the design under a variety of circumstances. As wireless networks become more complex, it is impractical to perform test- ing on a real deployment. As a result, the network administrators rely on network simulators or network emulators to validate their configurations and design. Unfortunately, network simulation falls short per it requires users to model the network behavior analytically. On the other hand, network emulation allows users to employ real network applications on virtualized network devices. Despite their complex design, the existing network emulation solutions miss full-scale automation rather they rely on experienced users to write complex configuration scripts making testing. Therefore, the validation process is prone to human operator errors. Further- more, they require a significant amount of computational resources that might not be feasible for many users. Moreover, most network emulators focus on lower layers of the network thus requiring users to employ their own network applications to control and measure network performance. To overcome these challenges, we propose a novel wireless network emulation platform, the system, that provides users a unified, high-level configuration interface for different layers of wireless networks to reduce management complexities of network emulators while having a generic, fully- automated platform. Menes is a generic, full-stack, fully-automated test and validation platform that empowers existing state-of-the- art emulation, virtualization, and network applications including performance measurement tools. We then provide an implementation of Menes based on the Extendable Mobile Ad-hoc Network Emulator (EMANE) with Docker containers. Our extensive evaluations show that the system requires much less computing resources, significantly decreases capital expenses (CAPEX) and operational expenses (OPEX), and greatly extensible for different use cases
Authors
  • Kerim Gokarslan (Yale)
Date Jun-2020
Venue arxiv pre-print [link]