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

2025-01-27

AI Summary

To address the challenge of resource management in dynamic, heterogeneous cloud–edge continuum environments—where flexibility, scalability, and global optimization are difficult to achieve simultaneously—this paper proposes a hybrid resource management architecture that integrates local autonomy with global coordination. Our approach introduces a novel joint framework combining Graph Neural Network (GNN)-driven state embedding with collaborative Multi-Agent Reinforcement Learning (MARL), enabling real-time, adaptive application deployment and scheduling via distributed state perception and hierarchical decision-making. Experimental evaluation on large-scale scenarios (up to 1,000 nodes) with dynamic topologies and workloads demonstrates a 19.3% improvement in resource utilization and a 32.7% reduction in task latency, significantly outperforming conventional centralized and fully decentralized baselines. The architecture achieves both decentralized scalability and system-level coordination accuracy.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Planning, Routing, and Scheduling: Mixed Discrete/Continuous Planning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

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.

Problem

• Resource Management
• Cloud Computing
• Edge Computing

Innovation

• Hybrid Centralized-Decentralized Approach
• Graph Neural Networks
• Autonomous Management in Cloud-Edge Environments