A Deep Learning Based RSA Strategy for Elastic Optical Networks
Authors:
- Jiaoliang YuJYJiaoliang Yu
- Bokai ChengBCBokai Cheng
- Cheng HangCHCheng Hang
- Yunfei HuYHYunfei Hu
- Shixin LiuSLShixin Liu
- Yutong WangYWYutong Wang
- Jianhua ShenJSJianhua Shen
- 1 August 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-3
Abstract
The dynamic allocation and release of services introduces spectrum fragmentation, which affects the allocation of subsequent services and utilization of spectrum resources for Elastic Optical Networks (EON). A deep learning based routing and spectrum assignments (RSA) strategy is proposed, which will find the optimal RSA method for a specific network, thus improving the overall network performance. Simulation results show that compared with the traditional RSA strategies, the neural network model used in this paper can improve the degree of spectrum fragmentation and reduce the network blocking probability.Keywords
This publication has 3 references indexed in Scilit:
- Deep-RMSA: A Deep-Reinforcement-Learning Routing, Modulation and Spectrum Assignment Agent for Elastic Optical Networks2018
- Distance Adaptive Dynamic Routing and Spectrum Allocation in Elastic Optical Networks with Shared Backup Path ProtectionJournal of Lightwave Technology, 2015
- Solving Routing and Spectrum Allocation Related Optimization Problems: From Off-Line to In-Operation Flexgrid Network PlanningJournal of Lightwave Technology, 2014