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.
@article{arxiv.2501.15802,
title = {Adaptive AI-based Decentralized Resource Management in the Cloud-Edge Continuum},
author = {Lanpei Li and Jack Bell and Massimo Coppola and Vincenzo Lomonaco},
journal= {arXiv preprint arXiv:2501.15802},
year = {2026}
}