Applications of Multi-Agent Deep Reinforcement Learning Communication in Network Management: A Survey

TL;DR

This survey reviews how multi-agent deep reinforcement learning with communication techniques is applied to automate and optimize various aspects of network management, highlighting recent advances and future challenges.

Contribution

It provides a comprehensive overview of MADRL applications in network management, focusing on communication strategies and open research issues.

Findings

MADRL effectively addresses non-stationarity in decentralized network management.

Communication schemes enhance cooperation among agents in complex environments.

Future research should focus on communication efficiency and scalability.

Abstract

With the advancement of artificial intelligence technology, the automation of network management, also known as Autonomous Driving Networks (ADN), is gaining widespread attention. The network management has shifted from traditional homogeneity and centralization to heterogeneity and decentralization. Multi-agent deep reinforcement learning (MADRL) allows agents to make decisions based on local observations independently. This approach is in line with the needs of automation and has garnered significant attention from academia and industry. In a distributed environment, information interaction between agents can effectively address the non-stationarity problem of multiple agents and promote cooperation. Therefore, in this survey, we first examined the application of MADRL in network management, including specific application fields such as traffic engineering, wireless network access, power control, and network security. Then, we conducted a detailed analysis of communication behavior between agents, including communication schemes, communication content construction, communication object selection, message processing, and communication constraints. Finally, we discussed the open issues and future research directions of agent communication in MADRL for future network management and ADN applications.