MetaFed: Advancing Privacy, Performance, and Sustainability in Federated Metaverse Systems

TL;DR

MetaFed introduces a decentralized federated learning framework for Metaverse systems that enhances privacy, reduces carbon footprint, and improves resource management through multi-agent reinforcement learning and renewable energy-aware scheduling.

Contribution

It presents MetaFed, a novel federated learning framework combining privacy preservation, sustainability, and dynamic resource orchestration tailored for Metaverse environments.

Findings

Achieves up to 25% reduction in carbon emissions.

Maintains high accuracy with minimal communication overhead.

Demonstrates scalability and environmental benefits in Metaverse applications.

Abstract

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.