Doherty, Michael;
Zhang, Yitao;
Beghelli, Alejandra;
(2023)
Masked deep reinforcement learning for virtual network embedding on elastic optical networks.
In:
Proceedings of the 2023 International Conference on Optical Network Design and Modeling (ONDM).
IEEE: Coimbra, Portugal.
(In press).
Preview |
Text
ONDM2023_Paper___Virtual_Network_Embedding_on_Elastic_Optical_Networks_with_Masked_Deep_Reinforcement_Learning (4).pdf - Other Download (304kB) | Preview |
Abstract
Deep reinforcement learning (DRL) with invalid action masking is applied to the optimization problem of virtual optical network embedding (VONE) over elastic optical networks (EON). Separate DRL agents are trained on the nodemapping task, link-mapping task, and overall VONE task. Their blocking probability performance is compared with a spectral fragmentation-aware VONE heuristic. All three DRL agents achieve lower blocking probability than the heuristic across low and high traffic loads.
| Type: | Proceedings paper |
|---|---|
| Title: | Masked deep reinforcement learning for virtual network embedding on elastic optical networks |
| Event: | 2023 International Conference on Optical Network Design and Modeling (ONDM) |
| Location: | Coimbra, Portugal |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://ieeexplore.ieee.org/xpl/conhome/10144828/p... |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | elastic optical network (EON), virtual network embedding (VNE), deep reinforcement learning (DRL) |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10175211 |
Archive Staff Only
 |
View Item |
