Semantic-Oriented Resource Allocation for Multi-Modal UAV Semantic Communication Networks
Han Hu, Xingwu Zhu, Fuhui Zhou, Wei Wu, Rose Qingyang Hu
Abstract
Semantic communication is envisioned as a potential communication paradigm based on artificial intelligence that holds the promise of breaking the Shannon limit for future 6G networks. This paradigm offers a promising opportunity for Unmanned Aerial Vehicles (UAVs) to conserve communication resources and minimize latency by only transmitting relevant semantic information. Despite the promising potential of UAV semantic communication networks, resource allocation in this context remains largely unexplored, particularly regarding multi-modal communication that adjusts the types of transmitted information (image, text, video, etc.) according to the task objectives and the available resources. This paper addresses the semantic-oriented resource allocation for multi-modal semantic communication with a focus on the UAV image-sensing task-oriented scenario. Firstly, a multi-modal semantic communication for the original image-sensing tasks of UAVs is designed. Subsequently, a semantic-level resource allocation problem based on the approximate semantic entropy and the semantic rate is formulated in terms of the transmit power allocation, channel assignment, and the number of transmitted semantic symbols. To solve the problem formulated, which involves a hybrid discrete-continuous action space, a novel algorithm called Hybrid-Decision-Controlled Deep Reinforcement Learning-based Semantic Communication Allocation (HDCD-SC) is introduced. The simulation results demonstrate that the proposed HDCD-SC algorithm can dynamically adjust the transmission modal according to the available resources, and achieve better performance in terms of latency, amount of semantic information, and notable reductions in energy and bandwidth costs when compared to other benchmarks.