BlockPred-DRL: A DRL Reward Design Method Based on CNN Blocking Prediction for RMSA in EON

Existing reward designs for DRL-based Routing, Modulation, and Spectrum Assignment (RMSA) in Elastic Optical Networks (EONs) often emphasize immediate allocation outcomes while neglecting the risk of future blocking. To address this limitation, we propose a DRL reward design that incorporates Convol...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Lingye Yang, Lei Wang, Hanyun Luo
Formato:	Artigo
Idioma:	Inglês
Publicado em:	IEEE 2026-01-01
Colecção:	IEEE Access
Assuntos:	Routing and spectrum assignment elastic optical network deep reinforcement learning convolutional neural network
Acesso em linha:	https://ieeexplore.ieee.org/document/11474482/
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!