Adaptive AI-based Decentralized Resource Management in the Cloud-Edge Continuum
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911426219606016 |
|---|---|
| author | Li, Lanpei Bell, Jack Coppola, Massimo Lomonaco, Vincenzo |
| author_facet | Li, Lanpei Bell, Jack Coppola, Massimo Lomonaco, Vincenzo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_15802 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adaptive AI-based Decentralized Resource Management in the Cloud-Edge Continuum Li, Lanpei Bell, Jack Coppola, Massimo Lomonaco, Vincenzo Distributed, Parallel, and Cluster Computing Artificial Intelligence 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. |
| title | Adaptive AI-based Decentralized Resource Management in the Cloud-Edge Continuum |
| topic | Distributed, Parallel, and Cluster Computing Artificial Intelligence |
| url | https://arxiv.org/abs/2501.15802 |