Robust Path Selection in Software-defined WANs using Deep Reinforcement Learning

no code implementations • 21 Dec 2022 • Shahrooz Pouryousef, Lixin Gao, Don Towsley

In the context of an efficient network traffic engineering process where the network continuously measures a new traffic matrix and updates the set of paths in the network, an automated process is required to quickly and efficiently identify when and what set of paths should be used.

reinforcement-learning Reinforcement Learning (RL)