Truthful mechanism for service utility maximization in edge-enabled metaverse based on NUMA

Abstract

The high-quality operation of the edge metaverse is heavily based on the efficient allocation and pricing of computational resources. Non-Uniform Memory Access (NUMA) architecture divides systems into multiple computing nodes with local processors and memory. These nodes enable independent computing and collaborative work, making them ideal for metaverse service demands while becoming increasingly prevalent. Despite the widespread use of incentive-based mechanism design in metaverse resource allocation, current studies often overlook the unique challenges posed by NUMA architecture, especially changes in resource topology and deployment rules. To address this gap, we propose a monotone heuristic algorithm for resource allocation that considers deployment constraints and resource dominance density. In addition, we design a pricing algorithm based on critical values, utilizing binary search to ensure the truthfulness of the mechanism. Simulation experiments demonstrate that our proposed mechanism achieves favorable outcomes in terms of system utility, final revenue, and resource utilization. The mechanism effectively balances the interests of both resource demanders and edge service providers to ensure reasonableness. Our results highlight the feasibility and effectiveness of integrating NUMA architecture into metaverse resource allocation and pricing strategies.