C-POD: An AWS Cloud Framework for Edge Pod Automation and Remote Wireless Testbed Sharing

This paper presents C-POD, a cloud-native framework that automates the deployment and management of edge pods for seamless remote access and sharing of wireless testbeds. C-POD leverages public cloud resources and edge pods to lower the barrier to over-the-air (OTA) experimentation, enabling researchers to share and access distributed testbeds without extensive local infrastructure. A supporting toolkit has been developed for C-POD to enable flexible and scalable experimental workflows, including containerized edge environments, persistent Secure Shell (SSH) tunnels, and stable graphical interfaces. We prototype and deploy C-POD on the Amazon Web Services (AWS) public cloud to demonstrate its key features, including cloud-assisted edge pod deployment automation, elastic computing resource management, and experiment observability, by integrating two wireless testbeds that focus on RF signal generation and 5G(B) communications, respectively.

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

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.