Hierarchical User Clustering for mmWave-NOMA Systems

Non-orthogonal multiple access (NOMA) and mmWave are two complementary technologies that can support the capacity demand that arises in 5G and beyond networks. The increasing number of users are served simultaneously while providing a solution for the scarcity of the bandwidth. In this paper we present a method for clustering the users in a mmWave-NOMA system with the objective of maximizing the sum-rate. An unsupervised machine learning technique, namely, hierarchical clustering is utilized which does the automatic identification of the optimal number of clusters. The simulations prove that the proposed method can maximize the sum-rate of the system while satisfying the minimum QoS for all users without the need of the number of clusters as a prerequisite when compared to other clustering methods such as k-means clustering.

Marasinghe Dileepa, Jayaweera Nalin, Rajatheva Nandana, Latva-ah Matti

Publication type:
A4 Article in conference proceedings

Place of publication:
2020 2nd 6G Wireless Summit (6G SUMMIT)

hierarchical clustering, Machine learning, mmWave, NOMA, user clustering


Full citation:
D. Marasinghe, N. Jayaweera, N. Rajatheva and M. Latva-Aho, “Hierarchical User Clustering for mmWave-NOMA Systems,” 2020 2nd 6G Wireless Summit (6G SUMMIT), Levi, Finland, 2020, pp. 1-5, doi: 10.1109/6GSUMMIT49458.2020.9083909


Read the publication here: