With the advance of mobile edge computing (MEC) and the Internet of Things (IoT), digital twin (dt) has become an emerging technology for provisioning IoT services between the real world and the cyber world. In this p...
详细信息
With the advance of mobile edge computing (MEC) and the Internet of Things (IoT), digital twin (dt) has become an emerging technology for provisioning IoT services between the real world and the cyber world. In this paper, we consider the state updating of dts in an MEC network through synchronizing dts with their physicalobjects. We make use of an energy-constrained UAV for data collection in a sensor network, as an illustrative example for the dt state updating of each object (sensor), and then use the dt data of objects (sensors) later for fidelity-aware query services. To this end, we first formulate a novel dt state staleness minimization, under a given update budget per update round. We then propose an optimal algorithm for a special case of the problem where the budget per update round is exactly K objects synchronizing with their dts. We then devise an algorithm for the dt state staleness minimization problem by reducing to the award collection maximization problem, assuming that the volume of the update data generated by each object per update round is given. Otherwise, we adopt a deep learning method to predict the volume of the update data. To demonstrate the importance of the dt state staleness in practical applications, we consider fidelity-aware query services in the MEC network, and we develop a cost-effective evaluation plan for each query. We finally evaluate the performance of the proposed algorithms through simulations. Simulation results demonstrate that the proposed algorithms are promising.
暂无评论