Reinforcement Learning-based Adaptive Path Selection for Programmable Networks
By: José Eduardo Zerna Torres , Marios Avgeris , Chrysa Papagianni and more
Potential Business Impact:
Makes internet traffic go faster by smart routing.
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.
Similar Papers
Reinforcement Learning-based Adaptive Path Selection for Programmable Networks
Machine Learning (CS)
Makes internet traffic go faster by smart routing.
Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning
Networking and Internet Architecture
Makes phones connect to the best signal automatically.
Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning
Networking and Internet Architecture
Makes phones connect to the best cell tower.