Multi-agent reinforcement learning for intent-based service assurance in cellular networks

by   Satheesh K. Perepu, et al.

Recently, intent-based management is receiving good attention in telecom networks owing to stringent performance requirements for many of the use cases. Several approaches on the literature employ traditional methods in the telecom domain to fulfill intents on the KPIs, which can be defined as a closed loop. However, these methods consider every closed-loop independent of each other which degrades the combined closed-loop performance. Also, when many closed loops are needed, these methods are not easily scalable. Multi-agent reinforcement learning (MARL) techniques have shown significant promise in many areas in which traditional closed-loop control falls short, typically for complex coordination and conflict management among loops. In this work, we propose a method based on MARL to achieve intent-based management without the requirement of the model of the underlying system. Moreover, when there are conflicting intents, the MARL agents can implicitly incentivize the loops to cooperate, without human interaction, by prioritizing the important KPIs. Experiments have been performed on a network emulator on optimizing KPIs for three services and we observe the proposed system performs well and is able to fulfill all existing intents when there are enough resources or prioritize the KPIs when there are scarce resources.


Lyapunov-Based Reinforcement Learning for Decentralized Multi-Agent Control

Decentralized multi-agent control has broad applications, ranging from m...

Modeling Sensorimotor Coordination as Multi-Agent Reinforcement Learning with Differentiable Communication

Multi-agent reinforcement learning has shown promise on a variety of coo...

SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning

The availability of challenging benchmarks has played a key role in the ...

Predictive Closed-Loop Service Automation in O-RAN based Network Slicing

Network slicing provides introduces customized and agile network deploym...

Multi-Objective Optimization of the Textile Manufacturing Process Using Deep-Q-Network Based Multi-Agent Reinforcement Learning

Multi-objective optimization of the textile manufacturing process is an ...

Mission-Critical Public Safety Networking: An Intent-Driven Service Orchestration Perspective

Intent-based networking (IBN) provides a promising approach for managing...

Please sign up or login with your details

Forgot password? Click here to reset