Deep Quantum-Transformer Networks for Multimodal Beam Prediction in ISAC Systems

In this article, we propose hybrid deep quantum-transformer networks (QTNs) to predict the optimal beam in integrated sensing and communication (ISAC) systems employing millimeter-wave (mmWave) band. In mobile applications, vehicle-to-infrastructure (V2I) communications at high frequency require large antenna arrays and narrow beams, which is associated with high-beam training overhead. In such a scenario, selecting an optimal beam to maximize the signal power at the receiver can be learned from the sensory data collected at the base station and guided by the position-based data provided by the user equipment. Such multimodal sensory data can be utilized by deep learning frameworks to create situational awareness for intelligently predicting optimal beams. We evaluate the proposed learning models in real-world V2I scenarios provided by the multimodal deepsense sixth generation data set and compare them with the existing works. The experimental results show a distance-based accuracy (DBA) score of 0.9124 for multimodal and 0.8832 for position-based data, respectively. Moreover, the hybrid QTN achieve the best DBA scores and the highest accuracy compared to other models on zero-shot testing. These QTN models exhibit low complexity and high performance, demonstrating their potential to address the challenges of beam management in mmWave ISAC systems.

I. Introduction

The advent of the sixth generation (6G) communication is set to revolutionize digital connectivity by offering high-data rates and ultralow latency by leveraging the extensive bandwidths in the millimeter-wave (mmWave) and sub-terahertz (THz) range [1], [2], [3]. The 6G network is envisioned to natively possess the situational awareness of the physical world through imaging and measuring the surrounding environment, referred to as integrated sensing and communication (ISAC) [4]. It complements emerging data-intensive and time-critical Internet of Everything (IoE) paradigm with vehicle-to-infrastructure (V2I) applications that digitally connect vehicles and the surrounding infrastructure by transforming road traffic signs, signals, and various facilities into digital formats and integrating sensing devices into this network [5], [6], [7], [8].