Hierarchical multi-agent deep reinforcement learning for SFC placement on multiple domains

Toumi, Nassima; Bagaa, Miloud; Ksentini, Adlen
LCN 2021, 46th Annual IEEE Conference on Local Computer Networks, 4-7 October 2021, Edmonton, Canada (Virtual Conference)

Service Function Chaining (SFC) is the process of decomposing a network service into multiple functions that successively process packets to deliver the end-to-end service. In
a multi-domain context, SFC placement is a challenging problem due to limited knowledge of the infrastructure of the local domains, which complicates the process of finding the optimal placement solutions. On the other hand, Reinforcement Learning
has gained momentum as a tool for decision-making, allowing agents to construct and improve policies using feedback from the environment. In this paper, we leverage Deep Reinforcement Learning (DRL) to perform SFC placement on multiple domains.
We devise a hierarchical architecture where the local domain agents and the multi-domain agent are trained using different DRL models to perform SFC and sub-SFC placement while satisfying the SLA requirements.

Communication systems
Eurecom Ref:
© 2021 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PERMALINK : https://www.eurecom.fr/publication/6604