DRL-based Slice Placement under Realistic Network Load Conditions

2021/09/27 by Esteves, José Jurandir Alves, Boubendir, Amina, Guillemin, Fabrice +1
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Networking and Internet Architecture (cs.NI)

paper · doi:10.48550/arxiv.2109.12857

Abstract

We propose to demonstrate a network slice placement optimization solution based on Deep Reinforcement Learning (DRL), referred to as Heuristically-controlled DRL, which uses a heuristic to control the DRL algorithm convergence. The solution is adapted to realistic networks with large scale and under non-stationary traffic conditions (namely, the network load). We demonstrate the applicability of the proposed solution and its higher and stable performance over a non-controlled DRL-based solution. Demonstration scenarios include full online learning with multiple volatile network slice placement request arrivals.

Related

• DRL-based Slice Placement Under Non-Stationary Conditions
• On the Robustness of Controlled Deep Reinforcement Learning for Slice Placement
• Controlled Deep Reinforcement Learning for Optimized Slice Placement
• A Heuristically Assisted Deep Reinforcement Learning Approach for Network Slice Placement
• DeepSlicing: Deep Reinforcement Learning Assisted Resource Allocation for Network Slicing