Sim2Field: End-to-End Development of AI RANs for 6G

2025-09-27

AI Summary

AI/ML models for cellular RAN suffer from poor generalizability and high validation costs due to a “performance gap” between simulation and real-world deployment. Method: This paper proposes Sim2Field—a methodology leveraging high-fidelity digital twins to enable site-specific physical-layer AI model training (e.g., channel estimation) and an end-to-end testbed supporting over-the-air evaluation with commercial user equipment. Contribution/Results: Sim2Field bridges the gap between simulation-based training and live-network deployment, significantly enhancing model adaptability to operational conditions. Field trials in a real-world 6G RAN demonstrate that the proposed AI-driven physical-layer algorithms achieve up to 40% throughput gain. To the best of our knowledge, this is the first systematic demonstration of the feasibility and practical value of AI-native wireless physical layers in commercial-grade environments.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Efficient ML / Green AI
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Large language models for search
• Security and Privacy: Security and privacy of machine learning and AI applications

Abstract

Following state-of-the-art research results, which showed the potential for significant performance gains by applying AI/ML techniques in the cellular Radio Access Network (RAN), the wireless industry is now broadly pushing for the adoption of AI in 5G and future 6G technology. Despite this enthusiasm, AI-based wireless systems still remain largely untested in the field. Common simulation methods for generating datasets for AI model training suffer from "reality gap" and, as a result, the performance of these simulation-trained models may not carry over to practical cellular systems. Additionally, the cost and complexity of developing high-performance proof-of-concept implementations present major hurdles for evaluating AI wireless systems in the field. In this work, we introduce a methodology which aims to address the challenges of bringing AI to real networks. We discuss how detailed Digital Twin simulations may be employed for training site-specific AI Physical (PHY) layer functions. We further present a powerful testbed for AI-RAN research and demonstrate how it enables rapid prototyping, field testing and data collection. Finally, we evaluate an AI channel estimation algorithm over-the-air with a commercial UE, demonstrating that real-world throughput gains of up to 40% are achievable by incorporating AI in the physical layer.

Problem

• Addressing the reality gap in AI wireless simulation training
• Reducing cost and complexity of AI-RAN field testing
• Bridging AI performance from simulation to practical cellular systems

Innovation

• Digital Twin simulations train site-specific AI PHY
• Testbed enables rapid prototyping and field testing
• AI channel estimation boosts throughput by 40%