CommUNext: Deep Learning-Based Cross-Band and Multi-Directional Signal Prediction

2025-11-08

AI Summary

Existing ray-tracing simulations for 6G full-spectrum cognition incur prohibitive computational overhead, while 5G inter-frequency measurement gaps degrade throughput, increase latency, and hinder scalability. Method: We propose a unified deep learning framework for cross-band, multi-directional signal strength prediction—from FR1 (sub-6 GHz) observations to FR3 (7–24 GHz). It features a dual-branch architecture: Full CommUNext replaces costly ray tracing for offline modeling; Partial CommUNext enables real-time completion of sparse high-frequency measurements. The framework jointly leverages low-frequency coverage maps, crowdsourced partial high-frequency samples, and spatial contextual features, incorporating a novel cross-frequency mapping mechanism. Contribution/Results: Under sparse supervision, our method achieves high accuracy and robustness, significantly reducing both simulation and field-measurement costs. It improves FR3 coverage modeling efficiency and spectrum utilization effectiveness, marking the first integration of offline modeling and online data imputation for millimeter-wave propagation cognition.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Online Learning & Bandits

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

Sixth-generation (6G) networks are envisioned to achieve full-band cognition by jointly utilizing spectrum resources from Frequency Range~1 (FR1) to Frequency Range~3 (FR3, 7--24,GHz). Realizing this vision faces two challenges. First, physics-based ray tracing (RT), the standard tool for network planning and coverage modeling, becomes computationally prohibitive for multi-band and multi-directional analysis over large areas. Second, current 5G systems rely on inter-frequency measurement gaps for carrier aggregation and beam management, which reduce throughput, increase latency, and scale poorly as bands and beams proliferate. These limitations motivate a data-driven approach to infer high-frequency characteristics from low-frequency observations. This work proposes CommUNext, a unified deep learning framework for cross-band, multi-directional signal strength (SS) prediction. The framework leverages low-frequency coverage data and crowd-aided partial measurements at the target band to generate high-fidelity FR3 predictions. Two complementary architectures are introduced: Full CommUNext, which substitutes costly RT simulations for large-scale offline modeling, and Partial CommUNext, which reconstructs incomplete low-frequency maps to mitigate measurement gaps in real-time operation. Experimental results show that CommUNext delivers accurate and robust high-frequency SS prediction even with sparse supervision, substantially reducing both simulation and measurement overhead.

Problem

• Physics-based ray tracing becomes computationally prohibitive for multi-band analysis
• Current 5G systems rely on measurement gaps that reduce throughput and increase latency
• There is a need to infer high-frequency characteristics from low-frequency observations

Innovation

• Deep learning predicts cross-band signal strength
• Leverages low-frequency data for high-frequency predictions
• Reduces simulation and measurement overhead significantly