Design and Evaluation of Next-Generation Cellular Networks through Digital and Physical Open and Programmable Platforms

TL;DR

The work addresses the complexity of next-generation cellular networks by combining large-scale digital twins with real-world private testbeds. It develops CaST to automate digital-twin scenario creation and validation on Colosseum, validates high-fidelity emulation against OTA Arena measurements, and delivers X5G—a GPU-accelerated, Open RAN private 5G testbed with near-RT control and a dApp framework. The dissertation demonstrates spectrum sharing, AI-driven radio-map modeling, and generative synthetic RF data (Gen-TWIN with soft-GAN) as core use cases in emulation, while deploying cuSense, InterfO-RAN, ORANSlice, and TIMESAFE on X5G to show real-time sensing, interference detection, dynamic slicing, and synchronization-security insights on physical platforms. Collectively, the work provides an end-to-end experimental pipeline bridging digital and physical layers to accelerate development, validation, and deployment of AI-native, Open RAN cellular networks with real-world relevance and strong security considerations.

Abstract

The evolution of the Radio Access Network (RAN) in 5G and 6G technologies marks a shift toward open, programmable, and softwarized architectures, driven by the Open RAN paradigm. This approach emphasizes open interfaces for telemetry sharing, intelligent data-driven control loops for network optimization, and virtualization and disaggregation of multi-vendor RAN components. While promising, this transition introduces significant challenges, including the need to design interoperable solutions, acquire datasets to train and test AI/ML algorithms for inference and control, and develop testbeds to benchmark these solutions. Experimental wireless platforms and private 5G deployments play a key role, providing architectures comparable to real-world systems and enabling prototyping and testing in realistic environments. This dissertation focuses on the development and evaluation of complementary experimental platforms: Colosseum, the world's largest Open RAN digital twin, and X5G, an open, programmable, multi-vendor private 5G O-RAN testbed with GPU acceleration. The main contributions include: (i) CaST, enabling automated creation and validation of digital twin wireless scenarios through 3D modeling, ray-tracing, and channel sounding; (ii) validation of Colosseum digital twins at scale, demonstrating that emulated environments closely reproduce real-world setups; (iii) X5G, integrating NVIDIA Aerial GPU-accelerated PHY processing with OpenAirInterface higher layers; (iv) a GPU-accelerated dApp framework for real-time RAN inference, enabling sub-millisecond control loops for AI-native applications including ISAC; and (v) intelligent RAN applications spanning spectrum sharing, interference detection, network slicing, security, and CSI-based sensing. Overall, this dissertation provides an end-to-end methodology bridging digital and physical experimentation for next-generation cellular networks.

Figures (115)

• Figure 1.1: Evolution of cellular networks from 1g to 6g, showing the progression in data rates, capabilities, and the increasing demands on next-generation systems.
• Figure 1.2: The Open RAN architecture, illustrating the transition from traditional closed-box base stations to disaggregated, software-defined, and intelligent network components connected through open interfaces polese2023understanding.
• Figure 1.3: Continuous growth in complexity, where modern cellular networks can be seen as a puzzle of interoperable hardware, software, and AI components.
• Figure 1.4: The journey of an experimental idea: from initial concept through design and simulation, to emulation at scale, to real-world ota testing, and finally to production deployment.
• Figure 2.5: High-level representation of digital twin components.