AMAC: attention-based multi-agent cooperation for smart load balancing - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

AMAC: attention-based multi-agent cooperation for smart load balancing

Résumé

In cooperative multi-agent reinforcement learning (MARL), efficient communication among agents requires the reduction of excessive message exchange at run-time to make it practical for real-world applications. This paper proposes a novel communication scheme, Attention-based Multi-Agent Cooperation (AMAC), that reduces overhead and shared information by exchanging only relevant messages across agents to coordinate decision-making and improve load balancing in networks. Experiments show that AMAC can significantly lower inter-agent communications overhead and learning complexity at the network controller level without degrading performance. The results demonstrate that our method actually outperforms multiple MARL benchmarks in Key Performance Indicators KPIs (such as throughput, delay, jitter), and Key Quality Indicators KQIs (such as QoE, average video bitrate, stalling).
Fichier principal
Vignette du fichier
AMAC_Attention-based Multi-Agent Cooperation for Smart Load Balancing.pdf (911.15 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03931985 , version 1 (10-01-2023)

Identifiants

Citer

Omar Houidi, Sihem Bakri, Djamal Zeghlache, Julien Lesca, Pham Tran Anh Quang, et al.. AMAC: attention-based multi-agent cooperation for smart load balancing. 2023 IEEE/IFIP Network Operations and Management Symposium (NOMS 2023), May 2023, Miami, FL, United States. ⟨10.1109/NOMS56928.2023.10154214⟩. ⟨hal-03931985⟩
44 Consultations
114 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More