Deep reinforcement learning for infrastructure as a service over flexible optical networks
M. Doherty,
A. Beghelli
Abstract:We apply a single deep reinforcement learning agent for dynamic virtual network provisioning. Benchmarked against state of the art heuristics, our approach achieves an order of magnitude lower blocking probability. Interpretability analysis provides insight to the agent's use of spectrum resources.
Set email alert for when this publication receives citations?
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.