Latency-Aware Heterogeneous Resource Allocation and Rendering Task Offloading for Metaverse

To deliver immersive experiences with the Metaverse, rendering must be carefully orchestrated in high-resolution environments with minimal latency. To address this fundamental challenge and NP-hard problem, in this paper, we consider joint computation, communication, and caching optimization in rendering using Edge Computing. With our Latency-aware, Resolution-focused, and Cache-optimized (LaReCa) framework involving heterogeneous resource allocation and rendering task offloading, we achieve the desired minimization of computational requirements and 25–30 % reduction of service latency without losing visual immersion compared with the SOTA baseline. Importantly, our LaReCa framework ensures the quality of immersion by surpassing normal HD resolution, which represents a substantial contribution to the broad landscape Metaverse rendering service.