Semantic-Aware Edge Intelligence for UAV Handover in 6G Networks

Abstract:
6G wireless networks aim to exploit semantic awareness for optimising the radio resources. By optimising the transmission through the lens of desired goal, energy consumption for transmissions can be reduced as well as latency can be improved. To that end, this paper investigates a paradigm where generative AI (GenAI) capabilities on the Edge are harnessed for network optimisation. In particular, we investigate Unmanned Aerial Vehicle (UAV) handover framework that leverages GenAI and semantic communication to maintain reliable connectivity. To that end, we propose a framework where a lightweight Mobile- BERT language model, fine-tuned using Low-Rank Adaptation (LoRA) is deployed on the UAV. This model processes multiattribute flight and radio measurements and performs multi-label classification to determine handover appropriate action. Concurrently, the model identifies an appropriate set of contextual ”Reason Tags” that elucidate the decision’s rationale. Our model evaluated on a rule-based synthetic dataset of UAV handover scenarios, demonstrates the model’s high efficacy in learning these rules, achieving high accuracy in predicting the primary handover decision. The model also shows strong performance in identifying supporting reasons, with an F1-micro score of approximately 0.9 for reason tags.