Transformer-Based Rate Prediction for Multi-Band Cellular Handsets

2025-09-29

AI Summary

Mobile multi-band cellular terminals face rapid channel variations and sparse measurements due to mobility, hand occlusion, and hardware constraints, severely hindering accurate cross-band throughput prediction. Method: This paper proposes a Transformer-based asynchronous multi-antenna–multi-band joint modeling framework. It is the first to leverage asynchronously sampled multi-array throughput time series for fine-grained throughput prediction in FR1/FR3 microcell scenarios. The model integrates ray-tracing simulation data to enhance physical interpretability and generalization. Contribution/Results: Evaluated in dense urban environments, the approach significantly improves prediction accuracy—reducing mean absolute error by 28.6% over baseline methods—and enhances band-selection reliability. It enables intelligent, low-overhead band scheduling for resource-constrained terminals without requiring synchronous multi-antenna measurements or real-time channel state feedback.

Technology Category

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

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Cellular wireless systems are witnessing the proliferation of frequency bands over a wide spectrum, particularly with the expansion of new bands in FR3. These bands must be supported in user equipment (UE) handsets with multiple antennas in a constrained form factor. Rapid variations in channel quality across the bands from motion and hand blockage, limited field-of-view of antennas, and hardware and power-constrained measurement sparsity pose significant challenges to reliable multi-band channel tracking. This paper formulates the problem of predicting achievable rates across multiple antenna arrays and bands with sparse historical measurements. We propose a transformer-based neural architecture that takes asynchronous rate histories as input and outputs per-array rate predictions. Evaluated on ray-traced simulations in a dense urban micro-cellular setting with FR1 and FR3 arrays, our method demonstrates superior performance over baseline predictors, enabling more informed band selection under realistic mobility and hardware constraints.

Problem

• Predicting achievable rates across multiple antenna arrays and bands
• Addressing sparse historical measurements in multi-band cellular systems
• Improving band selection under mobility and hardware constraints

Innovation

• Transformer neural network predicts multi-band rates
• Uses sparse historical measurements as input data
• Outperforms baselines in ray-traced urban simulations