Self-Maintained Network Digital Twin for Human-Centric Wireless Metaverse

Network digital twin is a key enabler for the human-centric wireless metaverse, requiring fine-grained replication, high-fidelity screen rendering, and the integration of emerging intelligent technologies. However, existing frameworks for the network digital twin overlook the integration of human-centric features within the metaverse and the importance of asynchronous data collection, both of which are indispensable for actualizing the metaverse and attaining self-maintenance capabilities. To address this issue, in this article, we propose a human-centric framework and a self-maintained mechanism for the network digital twin, utilizing continuous prediction and error tolerance to enhance the performance of DT decision-making. Specifically, by considering the interplay among different components, we present a human-centric framework for the network digital twin, comprising a device twin layer, a network twin layer, an artificial intelligence service layer, and a user intent layer. In consideration of asynchronous information, we propose a self-maintained mechanism facilitated by two key capabilities: error tolerance and continuous prediction. Furthermore, we conduct a resource allocation experiment to validate the efficiency of the proposed framework with request prediction and robust optimization. The results demonstrate that the framework can reduce the average latency compared to other baseline schemes, thus improving the user experience of wireless metaverse.