Reinforcement Learning-based Adaptive Path Selection for Programmable Networks

TL;DR

This paper introduces a distributed reinforcement learning framework for adaptive path selection in programmable networks, leveraging real-time telemetry and stochastic learning automata to improve network performance dynamically.

Contribution

It presents a novel in-network reinforcement learning approach combining SLA and INT for real-time, adaptive path selection in programmable networks.

Findings

The system converges to effective path choices in testbed scenarios.

It adapts dynamically to changing network congestion conditions.

Demonstrates real-time operation at line rate.

Abstract

This work presents a proof-of-concept implementation of a distributed, in-network reinforcement learning (IN-RL) framework for adaptive path selection in programmable networks. By combining Stochastic Learning Automata (SLA) with real-time telemetry data collected via In-Band Network Telemetry (INT), the proposed system enables local, data-driven forwarding decisions that adapt dynamically to congestion conditions. The system is evaluated on a Mininet-based testbed using P4-programmable BMv2 switches, demonstrating how our SLA-based mechanism converges to effective path selections and adapts to shifting network conditions at line rate.