Automated saturation mitigation controlled by deep reinforcement learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Automated saturation mitigation controlled by deep reinforcement learning

Résumé

Recent developments in orchestration and machine learning have made network automation more feasible, allowing the transition from error-prone and time-consuming manual manipulations to fast and refined automated responses in areas such as security and management. This article investigates the capabilities of a deep reinforcement learning agent to learn how to automatically share prefix announcements of an Autonomous System to its neighbors, in order to mitigate undesired network behaviors and therefore increase network resiliency and security. Our work focuses on network saturation, tackling the problem of network responsiveness in today's massive content delivery context. Results not only prove feasibility of such an agent, but also demonstrate its ability to minimize traffic loss as well as the number of actions to be performed by the automation process.
Fichier non déposé

Dates et versions

hal-03124039 , version 1 (28-01-2021)

Identifiants

Citer

Elkin Aguas, Anthony Lambert, Gregory Blanc, Hervé Debar. Automated saturation mitigation controlled by deep reinforcement learning. ICNP 2020: IEEE 28th International Conference on Network Protocols, Oct 2020, Madrid (online), Spain. pp.1-6, ⟨10.1109/ICNP49622.2020.9259356⟩. ⟨hal-03124039⟩
47 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More