Deep Reinforcement Learning based Decentralized Routing and Load-Balancing in Meshed QKD-Networks

Conference: ECOC 2024 - 50th European Conference on Optical Communication
09/22/2024 - 09/26/2024 at Frankfurt, Germany

Proceedings: ITG-Fb. 317: ECOC 2024

Pages: 4Language: englishTyp: PDF

Authors:
Johann, Tim; Kuehl, Sebastian; Pachnicke, Stephan

Abstract:
We present a deep reinforcement-learning (DRL) agent that routes encryption requests in a meshed QKD network autonomously in a decentralized manner without relying on a conventional shortest-path algorithm with linear weights. Our agent is able to reduce blocking of requests and simultaneously improves load-balancing.