A Multi-Agents Survivable Deep Reinforced Routing and Spectrum Assignment Algorithm in Elastic Optical Network

We propose an intelligent survivable RSA algorithm with multi agents based on deep reinforcement learning in EON to face multiple services and improve the survivability of network. Simulation result shows that the proposed algorithm can reduce packet loss rate and Improve resource utilization well.

Saved in:
Bibliographic Details
Published in2022 IEEE 12th International Conference on Electronics Information and Emergency Communication (ICEIEC) pp. 1 - 4
Main Authors Zhang, Zhidong, Luo, Zhihuan, Zhang, Wenchao, Yin, Shan, Huang, Shanguo, Wang, Xiaofeng, An, Ning, Luo, Zhen
Format Conference Proceeding
LanguageEnglish
Published IEEE 15.07.2022
Subjects
DQN
Dynamic scheduling
elastic optical networks
Heuristic algorithms
Optical fiber networks
Packet loss
Reinforcement learning
Routing
RSA
Simulation
survivality
Online AccessGet full text

Cover

More Information
Summary:We propose an intelligent survivable RSA algorithm with multi agents based on deep reinforcement learning in EON to face multiple services and improve the survivability of network. Simulation result shows that the proposed algorithm can reduce packet loss rate and Improve resource utilization well.
ISBN:9781665407533
1665407530
ISSN:2377-844X
DOI:10.1109/ICEIEC54567.2022.9835064