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

TL;DR

CommUNext is a deep learning framework that predicts high-frequency signal strength in 6G networks using low-frequency data, reducing reliance on costly simulations and measurements.

Contribution

It introduces a unified deep learning approach with two architectures to accurately infer high-frequency signals from low-frequency observations in 6G networks.

Findings

Accurately predicts high-frequency signal strength with sparse supervision.

Reduces computational and measurement overhead significantly.

Provides robust predictions even with incomplete data.

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, physicsbased 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 datadriven 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 lowfrequency 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.