Skip to Main content Skip to Navigation
Conference papers

DRL-based Slice Placement Under Non-Stationary Conditions

Abstract : We consider online learning for optimal network slice placement under the assumption that slice requests arrive according to a non-stationary Poisson process. We propose a framework based on Deep Reinforcement Learning (DRL) combined with a heuristic to design algorithms. We specifically design two pure-DRL algorithms and two families of hybrid DRL-heuristic algorithms. To validate their performance, we perform extensive simulations in the context of a large-scale operator infrastructure. The evaluation results show that the proposed hybrid DRL-heuristic algorithms require three orders of magnitude of learning episodes less than pure-DRL to achieve convergence. This result indicates that the proposed hybrid DRLheuristic approach is more reliable than pure-DRL in a real non-stationary network scenario.
Complete list of metadata

https://hal.inria.fr/hal-03332502
Contributor : Pierre Sens Connect in order to contact the contributor
Submitted on : Thursday, September 2, 2021 - 6:02:05 PM
Last modification on : Wednesday, June 8, 2022 - 12:50:07 PM
Long-term archiving on: : Friday, December 3, 2021 - 9:06:29 PM

File

CNSM2021.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03332502, version 1

Citation

Jose Jurandir Alves Esteves, Amina Boubendir, Fabrice Guillemin, Pierre Sens. DRL-based Slice Placement Under Non-Stationary Conditions. CNSM 2021 - 17th International Conference on Network and Service Management, Oct 2021, Izmir, Turkey. ⟨hal-03332502⟩

Share

Metrics

Record views

66

Files downloads

74