Open AccessRouting based on Reinforcement Learning for Software-Defined Networking
Author(s) -
Daniela Maria Casas Velasco,
N Fonseca,
Óscar Mauricio Caicedo Rendón
Publication year - 2021
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/sbrc_estendido.2021.17170
Subject(s) - policy based routing , computer science , reinforcement learning , static routing , distributed computing , link state routing protocol , dynamic source routing , routing domain , computer network , multipath routing , routing (electronic design automation) , equal cost multi path routing , routing protocol , artificial intelligence
Traditional routing protocols employ limited information to make routing decisions, leading to slow adaptation to traffic variability and restricted support to applications quality of service requirements. This paper introduces the work developed in the MSc. thesis entitled "Routing based on Reinforcement Learning for Software-Defined Networking", which defines routing approaches based on (deep) reinforcement learning. The results show that our solutions surpass routing algorithms based on Dijkstra as well as they are practical and feasible solutions for routing in Software-Defined Networking.