On the Robustness of Controlled Deep Reinforcement Learning for Slice Placement

Jose Jurandir Alves Esteves (1, 2) , Amina Boubendir (2) , Fabrice Guillemin (2) , Pierre Sens (1)

1 DELYS - DistributEd aLgorithms and sYStems
2 Orange Labs

The evaluation of the impact of using Machine Learning in the management of softwarized networks is considered in multiple research works. In this paper, we propose to evaluate the robustness of online learning for optimal network slice placement. A major assumption in this study is to consider that slice request arrivals are non-stationary. We precisely simulate unpredictable network load variations and compare two Deep Reinforcement Learning (DRL) algorithms: a pure DRL-based algorithm and a heuristically controlled DRL as a hybrid DRL-heuristic algorithm, in order to assess the impact of these unpredictable changes of traffic load on the algorithms performance. We conduct extensive simulations of a large-scale operator infrastructure. The evaluation results show that the proposed hybrid DRL-heuristic approach is more robust and reliable than pure DRL in real network scenarios.

Mots clés: Network Slicing Placement Optimization Deep Reinforcement Learning Robustness Reliability; Network Slicing; Placement; Optimization; Deep Reinforcement Learning; Robustness; Reliability

Domaines: Réseaux et télécommunications [cs.NI]

Jose Jurandir Alves Esteves, Amina Boubendir, Fabrice Guillemin, Pierre Sens. On the Robustness of Controlled Deep Reinforcement Learning for Slice Placement. Journal of Network and Systems Management, 2022, 30 (3), pp.43. ⟨10.1007/s10922-022-09654-8⟩. ⟨hal-03954527⟩