Tiny-Twin: A CPU-Native Full-stack Digital Twin for NextG Cellular Networks

TL;DR

Tackling the need for realistic, repeatable NextG testing, the paper addresses the gap between costly hardware emulators and abstract simulators. It introduces Tiny-Twin, a CPU-native, full-stack digital twin that runs on commodity hardware, using time-varying multi-tap channel convolution, channel replay, OpenAirInterface integration, per-UE isolation, and real-time RIC control to reproduce end-to-end wireless behavior. The authors provide design principles for high fidelity, implement optimizations (UE-localized convolution, sparse taps, CPU pinning), and demonstrate real-time performance with up to 10 UEs and 20 taps per UE, achieving around $2$ ms $TTI$ latency and stable $RTT$ across channel dynamics. They also release an open-source Grafana-based monitoring framework and validate the framework against diverse channel traces (3GPP, ray-traced, ARGOS), underscoring its practical impact for AI-driven RAN research and reproducible experimentation.

Abstract

Modern wireless applications demand testing environments that capture the full complexity of next-generation (NextG) cellular networks. While digital twins promise realistic emulation, existing solutions often compromise on physical-layer fidelity and scalability or depend on specialized hardware. We present Tiny-Twin, a CPU-Native, full-stack digital twin framework that enables realistic, repeatable 5G experimentation on commodity CPUs. Tiny-Twin integrates time-varying multi-tap convolution with a complete 5G protocol stack, supporting plug-and-play replay of diverse channel traces. Through a redesigned software architecture and system-level optimizations, Tiny-Twin supports fine-grained convolution entirely in software. With built-in real-time RIC integration and per User Equipment(UE) channel isolation, it facilitates rigorous testing of network algorithms and protocol designs. Our evaluation shows that Tiny-Twin scales to multiple concurrent UEs while preserving protocol timing and end-to-end behavior, delivering a practical middle ground between low-fidelity simulators and high-cost hardware emulators. We release Tiny-Twin as an open-source platform to enable accessible, high-fidelity experimentation for NextG cellular research.

Figures (7)

• Figure 1: Tiny-Twin Overview: Building a low-cost high-fidelity Digital Twin for Wireless Cellular Networks
• Figure 2: Challenges with Vanilla system
• Figure 3: Tiny-twin system design and benchmarks
• Figure 4: Sanity Check of channel impelemetation on Tiny-twin
• Figure 5: Plug-N-Play Channels on Tiny-twin