Adaptive AI-based Decentralized Resource Management in the Cloud-Edge Continuum

TL;DR

This paper introduces a hybrid framework combining Graph Neural Networks and multi-agent reinforcement learning to enable adaptive, scalable, and efficient resource management across cloud and edge infrastructures with decentralized decision-making and centralized oversight.

Contribution

It presents a novel hybrid approach integrating GNNs and collaborative MARL for resource management in the Cloud-Edge Continuum, balancing decentralization with global coordination.

Findings

Enhanced adaptability to dynamic workloads

Improved resource utilization efficiency

Scalable decision-making framework

Abstract

In the Cloud-Edge Continuum, dynamic infrastructure change and variable workloads complicate efficient resource management. Centralized methods can struggle to adapt, whilst purely decentralized policies lack global oversight. This paper proposes a hybrid framework using Graph Neural Network (GNN) embeddings and collaborative multi-agent reinforcement learning (MARL). Local agents handle neighbourhood-level decisions, and a global orchestrator coordinates system-wide. This work contributes to decentralized application placement strategies with centralized oversight, GNN integration and collaborative MARL for efficient, adaptive and scalable resource management.