Quantum Machine Learning for Controller Placement in Software Defined Networks
Konferenz: European Wireless 2023 - 28th European Wireless Conference
02.10.2023-04.10.2023 in Rome, Italy
Tagungsband: European Wireless 2023
Seiten: 6Sprache: EnglischTyp: PDF
Autoren:
Shekhar Nande, Swaraj; Biswas, Sonai (Deutsche Telekom Chair of Communication Networks, Technische Universität Dresden, Germany & Quantum Communication Networks (QCNets) research group, Technische Universität Dresden, Germany)
Lhamo, Osel; Fitzek, Frank H. P. (Deutsche Telekom Chair of Communication Networks, Technische Universität Dresden, Germany)
Bassoli, Riccardo (Deutsche Telekom Chair of Communication Networks, Technische Universität Dresden, Germany & Centre for Tactile Internet with Human-in-the-Loop (CeTI), Cluster of Excellence, Dresden, Germany & Quantum Communication Networks (QCNets) research group, Technische Universität Dresden, Germany)
Inhalt:
As the number of dynamic applications grows, so does the demand for Network Programming Interoperability, resulting in the birth of Software Defined Networking. Novel sources, including quantum technologies, are required to enable the shift to a software-centric and autonomous next-generation 6G network with integrated intelligence. In this research, we use quantum machine learning to provide a unique technique for addressing the issue of SDN controller placement inside a multi-controller. We evaluate the proposed strategy’s efficacy by analyzing simulation results and considering the polylogarithmic computational cost associated with QML algorithms. The evaluation, focused on latency metrics, reveals that QML can resolve the SDN clustering problem with latencies equivalent to those observed in classical machine learning methods such as K-means. This study marks the first application of QML to the controller placement issue in SDN, signifying its potential to influence the design and development of future 6G networks and the quantum internet.