AMAC: Attention-based Multi-Agent Cooperation for Smart Load Balancing

This paper proposes an Attention-based Multi-Agent Cooperation (AMAC) approach to reduce message exchange overhead in Multi-Agent Reinforcement Learning-based smart load balancing. AMAC shares only most relevant messages across agents to coordinate decision-making without degrading original performa...

Full description

Saved in:
Bibliographic Details
Published inNOMS 2023-2023 IEEE/IFIP Network Operations and Management Symposium pp. 1 - 7
Main Authors Houidi, Omar, Bakri, Sihem, Zeghlache, Djamal, Lesca, Julien, Quang, Pham Tran Anh, Leguay, Jeremie, Medagliani, Paolo
Format Conference Proceeding
LanguageEnglish
Published IEEE 08.05.2023
Subjects
Benchmark testing
Complexity theory
Decision making
Information exchange
Key performance indicator
Load management
Machine learning algorithms
Multi-Agent
Overhead reduction
QoE Optimization
Reinforcement Learning
Smart Load Balancing
Online AccessGet full text

Cover

More Information
Summary:This paper proposes an Attention-based Multi-Agent Cooperation (AMAC) approach to reduce message exchange overhead in Multi-Agent Reinforcement Learning-based smart load balancing. AMAC shares only most relevant messages across agents to coordinate decision-making without degrading original performance. Experiments show that AMAC significantly lowers inter-agent communications overhead and learning complexity and outperforms multiple MARL benchmarks in Key Performance Indicators (KPIs) and Key Quality Indicators (KQIs).
ISSN:2374-9709
DOI:10.1109/NOMS56928.2023.10154214