%0 Conference Proceedings
%T Self-learning Routing for Optical Networks
%+ Sun Yat-sen University [Guangzhou] (SYSU)
%+ XenLink Co. Ltd.
%+ University of Bristol [Bristol]
%A Huang, Yue-Cai
%A Zhang, Jie
%A Yu, Siyuan
%Z Part 2: Poster Papers
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 23th International IFIP Conference on Optical Network Design and Modeling (ONDM)
%C Athens, Greece
%Y Anna Tzanakaki
%Y Manos Varvarigos
%Y Raul Muñoz
%Y Reza Nejabati
%Y Noboru Yoshikane
%Y Markos Anastasopoulos
%Y Johann Marquez-Barja
%I Springer International Publishing
%3 Optical Network Design and Modeling
%V LNCS-11616
%P 467-478
%8 2019-05-13
%D 2019
%R 10.1007/978-3-030-38085-4_40
%K Optical networks
%K Routing
%K Self-learning
%Z Computer Science [cs]
%Z Computer Science [cs]/Networking and Internet Architecture [cs.NI]Conference papers
%X It is generally very difficult to optimize the routing policies in optical networks with dynamic traffic. Most widely-used routing policies, e.g., shortest path routing and least congested path (LCP) routing, are heuristic policies. Although the LCP is often regarded as the best-performing adaptive routing policy, we are often eager to know whether there exist better routing policies that surpass these heuristics in performance. In this paper, we propose a framework of reinforcement learning (RL) based routing scheme, that learns routing decisions during the interactions with the environment. With a proposed self-learning method, the RL agent can improve its routing policy continuously. Simulations on a ring-topology metro optical network demonstrate that, the proposed scheme outperforms the LCP routing policy.
%G English
%Z TC 6
%Z WG 6.10
%2 https://inria.hal.science/hal-03200673/document
%2 https://inria.hal.science/hal-03200673/file/484327_1_En_40_Chapter.pdf
%L hal-03200673
%U https://inria.hal.science/hal-03200673
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-TC
%~ IFIP-WG
%~ IFIP-TC6
%~ IFIP-LNCS-11616
%~ IFIP-ONDM
%~ IFIP-WG6-10