Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Intelligent Spectrum Management in 5G Mobile Networks based on Recurrent Neural Networks
Ist Teil von
2019 IEEE 15th International Conference on the Experience of Designing and Application of CAD Systems (CADSM), 2019, p.1-4
Ort / Verlag
IEEE
Erscheinungsjahr
2019
Quelle
IEEE Xplore
Beschreibungen/Notizen
Tremendous traffic growth in modern mobile networks requires complete rethinking of the spectrum management in order to provide high network throughput in conditions of limited spectral resources. In this paper, we propose a new approach for intelligent spectrum management based on the recurrent neural networks. The key idea of the proposed solution is to use long and short term traffic prediction in each particular cell and correspondingly update spectrum allocation taking into account the spectral efficiency and interference among the cells. Simulation results show that the proposed approach is able to achieve 90% accuracy of the spectrum allocation with low computational complexity.