ScholarWorks@성균관대학교

초록

In this paper, we investigate the joint data relay communication and semantic communication in an unmaned aerial vehicle (UAV)-based Metaverse system. Therein, UAVs as relays forward data from ground users to ground data collectors (GDCs). Meanwhile, they capture images of area of interests, and the images can be used to update digital twin (DTs) for Metaverse platforms. As the UAVs and their GDCs may belong to different platforms, they may use the same spectrum at the same time that cause interference to each other. A third party, i.e., a network service provider (NSP), is involved to provide licensed channels in terms of transmission periods to the UAVs. We design auction schemes as incentive mechanisms for trading the transmission periods between the UAVs and the NSP. With a single transmission period, we design a learning auction with neural networks constructed from the Myerson theorem that maximizes the NSP's revenue while ensuring important economic properties. With multiple transmission periods, we develop a nearly-optimal auction scheme by using attention mechanisms. A semantic communication technique is implemented at each UAV to reduce the size of the original images and cost for using the licensed channels. Extensive experiments shows that the learning auction driven from the Myerson theorem outperform the baseline scheme in terms of NSP's revenue and truthfulness, while the revenue obtained by the attention-based auction is much higher than the existing learning auction. © IEEE. 1972-2012 IEEE.

키워드