Controlled Deep Reinforcement Learning for Optimized Slice Placement

2021/08/03 by Esteves, Jose Jurandir Alves, Boubendir, Amina, Guillemin, Fabrice +1
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Networking and Internet Architecture (cs.NI)

paper · doi:10.48550/arxiv.2108.01544

Abstract

We present a hybrid ML-heuristic approach that we name "Heuristically Assisted Deep Reinforcement Learning (HA-DRL)" to solve the problem of Network Slice Placement Optimization. The proposed approach leverages recent works on Deep Reinforcement Learning (DRL) for slice placement and Virtual Network Embedding (VNE) and uses a heuristic function to optimize the exploration of the action space by giving priority to reliable actions indicated by an efficient heuristic algorithm. The evaluation results show that the proposed HA-DRL algorithm can accelerate the learning of an efficient slice placement policy improving slice acceptance ratio when compared with state-of-the-art approaches that are based only on reinforcement learning.

Related

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