On the Effects of Modeling on the Sim-to-Real Transfer Gap in Twinning the POWDER Platform

TL;DR

This paper investigates how different modeling choices affect the transfer of wireless network algorithms from simulation to real-world deployment in a digital twin of the POWDER platform, highlighting key factors for effective sim-to-real transfer.

Contribution

It provides an analysis of path loss models in a digital twin of the POWDER platform, offering insights into model selection for improved sim-to-real transfer in wireless systems.

Findings

Path loss model choice significantly impacts transfer accuracy.

Accurate 3D modeling improves simulation realism.

Guidelines for digital twin implementation in wireless networks.

Abstract

Digital Twin (DT) technology is expected to play a pivotal role in NextG wireless systems. However, a key challenge remains in the evaluation of data-driven algorithms within DTs, particularly the transfer of learning from simulations to real-world environments. In this work, we investigate the sim-to-real gap in developing a digital twin for the NSF PAWR Platform, POWDER. We first develop a 3D model of the University of Utah campus, incorporating geographical measurements and all rooftop POWDER nodes. We then assess the accuracy of various path loss models used in training modeling and control policies, examining the impact of each model on sim-to-real link performance predictions. Finally, we discuss the lessons learned from model selection and simulation design, offering guidance for the implementation of DT-enabled wireless networks.