Urban Sensing of Virtual Internet of Things for Metaverse

Urban sensing encourages the incredibly quick advancement of digitalization, intelligence, and ubiquitous perception, accelerating the construction of the metaverse. Various sensors construct the sensing network to capture human activities for the human-centered metaverse. However, effective management of ubiquitous urban sensing with various attributes is a challenge. In this paper, we propose a Virtual Internet of Things (VIoT) enabled by digital twin (DT) for building the metaverse. Specifically, we introduce an architecture of VIoT, including a policy sensing layer, a 6G edge-cloud collaboration layer, a DT layer, and a user-friendly terminal layer. Furthermore, to address the sensing scheduling issue in the VIoT, we formulate a sensing profit maximization problem by considering the sensing coverage, data utility, and energy cost attributes of visual sensors and fabric sensors. To tackle this problem efficiently, we design a sensing scheduling policy based on the soft actor-critic (SSP-SAC) algorithm. The simulation results demonstrated that compared to the baseline schemes, the SSP-SAC scheme can significantly improve the sensing profit in diverse situations, indicating that the VIoT can provide an effective urban sensing policy.