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

TL;DR

This paper tackles dynamic resource management in the Cloud-Edge Continuum by proposing a hybrid decentralized framework that marries Graph Neural Network embeddings with collaborative Multi-Agent Reinforcement Learning. Local agents handle neighborhood-level placement decisions while a global orchestrator aligns system-wide objectives, addressing scalability, adaptability, and accuracy in highly dynamic environments. The approach includes a formal system and cost model, dual observation/action spaces for local/global agents, and an optimization stack featuring GNN embeddings, MARL, and customized experience replay. The proposed framework aims to deliver improved SLA adherence and resource utilization in a scalable, adaptive manner suitable for real-world edge-cloud deployments.

Abstract

The increasing complexity of application requirements and the dynamic nature of the Cloud-Edge Continuum present significant challenges for efficient resource management. These challenges stem from the ever-changing infrastructure, which is characterized by additions, removals, and reconfigurations of nodes and links, as well as the variability of application workloads. Traditional centralized approaches struggle to adapt to these changes due to their static nature, while decentralized solutions face challenges such as limited global visibility and coordination overhead. This paper proposes a hybrid decentralized framework for dynamic application placement and resource management. The framework utilizes Graph Neural Networks (GNNs) to embed resource and application states, enabling comprehensive representation and efficient decision-making. It employs a collaborative multi-agent reinforcement learning (MARL) approach, where local agents optimize resource management in their neighborhoods and a global orchestrator ensures system-wide coordination. By combining decentralized application placement with centralized oversight, our framework addresses the scalability, adaptability, and accuracy challenges inherent in the Cloud-Edge Continuum. This work contributes to the development of decentralized application placement strategies, the integration of GNN embeddings, and collaborative MARL systems, providing a foundation for efficient, adaptive and scalable resource management.