Adapting Wireless Mesh Network Configuration from Simulation to Reality via Deep Learning based Domain Adaptation

Recent years have witnessed the rapid deployments of wireless mesh networks (WMNs) for industrial automation, military operations, smart energy, etc. Although WMNs work satisfactorily most of the time thanks to years of research, they are often difficult to configure as configuring a WMN is a complex process, which involves theoretical computation, simulation, and field testing, among other tasks. Simulating a WMN provides distinct advantages over experimenting on a physical network when it comes to identifying a good network configuration. Unfortunately, our study shows that the models for network configuration prediction learned from simulations cannot always help physical networks meet performance requirements because of the simulation-to-reality gap. In this paper, we employ deep learning based domain adaptation to close the gap and leverage a teacher-student neural network to transfer the network configuration knowledge learned from a simulated network to its corresponding physical network. Experimental results show that our method effectively closes the gap and increases the accuracy of predicting a good network configuration that allows the network to meet performance requirements from 30.10% to 70.24% by learning robust machine learning models from a large amount of inexpensive simulation data and a few costly field testing measurements.