MetaFed: Advancing Privacy, Performance, and Sustainability in Federated Metaverse Systems
This addresses the problem of building scalable, environmentally responsible, and privacy-compliant Metaverse infrastructures, representing an incremental improvement through integration of existing techniques.
The paper tackles the challenges of performance, privacy, and sustainability in Metaverse systems by proposing MetaFed, a federated learning framework that reduces carbon emissions by up to 25% while maintaining high accuracy.
The rapid expansion of immersive Metaverse applications introduces complex challenges at the intersection of performance, privacy, and environmental sustainability. Centralized architectures fall short in addressing these demands, often resulting in elevated energy consumption, latency, and privacy concerns. This paper proposes MetaFed, a decentralized federated learning (FL) framework that enables sustainable and intelligent resource orchestration for Metaverse environments. MetaFed integrates (i) multi-agent reinforcement learning for dynamic client selection, (ii) privacy-preserving FL using homomorphic encryption, and (iii) carbon-aware scheduling aligned with renewable energy availability. Evaluations on MNIST and CIFAR-10 using lightweight ResNet architectures demonstrate that MetaFed achieves up to 25% reduction in carbon emissions compared to conventional approaches, while maintaining high accuracy and minimal communication overhead. These results highlight MetaFed as a scalable solution for building environmentally responsible and privacy-compliant Metaverse infrastructures.