Deep Reinforcement Learning based Decentralized Routing and Load-Balancing in Meshed QKD-Networks
Konferenz: ECOC 2024 - 50th European Conference on Optical Communication
22.09.2024-26.09.2024 in Frankfurt, Germany
Tagungsband: ITG-Fb. 317: ECOC 2024
Seiten: 4Sprache: EnglischTyp: PDF
Autoren:
Johann, Tim; Kuehl, Sebastian; Pachnicke, Stephan
Inhalt:
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.