Multimodal Large Language Model Enabled Robust Beamforming for HAP Downlink Communications
2026-04-10 • Networking and Internet Architecture
Networking and Internet Architecture
AI summaryⓘ
The authors address how small changes in the position of high altitude platforms (HAPs) can mess up the direction of their communication beams, causing poor signal quality. They created a special AI model that uses flight data and visual information to predict these changes quickly and adjust the beams in advance. Their approach includes a way to check and reduce prediction errors for better reliability. Their tests show improved service quality and speed compared to existing methods, with delays low enough for real-world use.
High Altitude Platform (HAP)BeamformingLarge Language Model (LLM)Vision-Language ModelFlight TelemetryProactive Beam SteeringQuality of Service (QoS)Forecast Error CalibrationUser Service RatioSum-Rate
Authors
Xiaoyu Xing, Peng Yang, Guoquan Tao, Dingyi Lu, Zehui Xiong, Xianbin Cao
Abstract
Small changes in high altitude platform (HAP) attitude can cause significant deviations in HAP downlink beam directions, thereby severely degrading HAP downlink communication performance. In this paper, we develop a multimodal large language model (LLM) enabled beamforming framework to achieve robust HAP downlink communications.Specifically, we design a vision-language LLM (VL-LLM) that learns from multivariate flight telemetry to forecast short-term HAP attitudes under platform shaking and support delay-aware proactive beam steering.We design an offline forecast-error calibration procedure to obtain upper bounds on forecast errors and improve the reliability of proactive analog beam steering.Based on the attitude forecasts, we proactively update the analog beamformer and propose a QoS-driven beamforming and admission method with a lightweight feasibility-enforcement step to satisfy instantaneous transmit-power and QoS requirements.Simulation results indicate that the designed VL-LLM can accurately capture changes in the HAP attitude and the proposed beamforming method achieves a 22.1% higher user service ratio and a 12.5% higher sum-rate than representative baselines.The measured mean and p99 total latencies are 36.24 ms and 40.13 ms, respectively, supporting practical delay-aware deployment.