6G Twin: Hybrid Gaussian Radio Fields for Channel Estimation and Non-Linear Precoder Design for Radio Access Networks

2025-09-23

AI Summary

This paper addresses three key challenges in 6G radio access networks (RANs): high-overhead channel state information (CSI) acquisition, inaccurate channel prediction during mobility-induced handovers, and energy-inefficient nonlinear precoding. To this end, it proposes the first end-to-end AI-native RAN framework. Methodologically: (1) a neural Gaussian radio frequency field enables implicit CSI compression, drastically reducing pilot overhead; (2) a replay-driven continual learning mechanism ensures robust cross-cell channel tracking under mobility; and (3) an order-agnostic convex optimization-based minPMAC precoder jointly optimizes transmission scheduling and energy efficiency. The contribution is a GPU-ready real-time network twin system supporting millisecond-scale closed-loop control and seamless handover. Experiments demonstrate a 100× reduction in CSI overhead, >10 dB NMSE improvement in handover scenarios, 4–10× lower energy consumption, up to 5× higher spectral efficiency at equal transmit power, and monotonically increasing energy efficiency with SNR.

Technology Category

• Machine Learning: Efficient ML / Green AI
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

This work introduces 6G Twin, the first end-to-end artificial intelligence (AI)-native radio access network (RAN) design that unifies (i) neural Gaussian Radio Fields (GRF) for compressed channel state information (CSI) acquisition, (ii) continual channel prediction with handover persistence, and (iii) an energy-optimal nonlinear precoder (minPMAC). GRF replaces dense pilots with a sparse Gaussian field, cutting pilot overhead by about 100x while delivering 1.1 ms inference and less than 2 minutes on-site training, thus enabling millisecond-scale closed-loop operation. A replay-driven continual learner sustains accuracy under mobility and cell transitions, improving channel normalized mean square error (NMSE) by more than 10 dB over frozen predictors and an additional 2-5 dB over uniform replay, thereby stabilizing performance across UMi/UMa handovers. Finally, minPMAC solves a convex, order-free MAC precoder design that recovers the globally optimal order from Broadcast Channel (BC) duals and minimizes transmit energy subject to minimum-rate guarantees, achieving 4-10 times lower energy (scenario dependent) with monotonically increasing bits per joule as SNR grows. This translates to up to 5 times higher data rate at comparable power or the same rates at substantially lower power. Together, these components form a practical, GPU-ready framework that attains real-time CSI, robust tracking in dynamic networks with efficient handovers, and state-of-the-art throughput-energy tradeoffs under 3GPP-style settings.

Problem

• Reduces pilot overhead by 100x using sparse Gaussian fields for channel estimation
• Maintains channel prediction accuracy during mobility and cell handovers
• Minimizes transmit energy while guaranteeing minimum data rates

Innovation

• Neural Gaussian Radio Fields for compressed CSI acquisition
• Replay-driven continual learning for mobility and handovers
• Convex order-free precoder minimizing transmit energy