A Heuristically Assisted Deep Reinforcement Learning Approach for Network Slice Placement - Archive ouverte HAL Access content directly
Journal Articles IEEE Transactions on Network and Service Management Year : 2021

A Heuristically Assisted Deep Reinforcement Learning Approach for Network Slice Placement

(1, 2) , (2) , (2) , (1)
1
2

Abstract

Network Slice placement with the problem of allocation of resources from a virtualized substrate network is an optimization problem which can be formulated as a multiobjective Integer Linear Programming (ILP) problem. However, to cope with the complexity of such a continuous task and seeking for optimality and automation, the use of Machine Learning (ML) techniques appear as a promising approach. We introduce a hybrid placement solution based on Deep Reinforcement Learning (DRL) and a dedicated optimization heuristic based on the "Power of Two Choices" principle. The DRL algorithm uses the so-called Asynchronous Advantage Actor Critic (A3C) algorithm for fast learning, and Graph Convolutional Networks (GCN) to automate feature extraction from the physical substrate network. The proposed Heuristically-Assisted DRL (HA-DRL) allows for the acceleration of the learning process and substantial gain in resource usage when compared against other state-of-theart approaches, as evidenced by evaluation results.
Fichier principal
Vignette du fichier
TNSM-2022.pdf (4 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03954579 , version 1 (24-01-2023)

Identifiers

Cite

Jose Jurandir Alves Esteves, Amina Boubendir, Fabrice Guillemin, Pierre Sens. A Heuristically Assisted Deep Reinforcement Learning Approach for Network Slice Placement. IEEE Transactions on Network and Service Management, 2021, pp.1-1. ⟨10.1109/TNSM.2021.3132103⟩. ⟨hal-03954579⟩
0 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More