Learning-Assisted User Clustering in Cell-Free Massive MIMO-NOMA Networks

The superior spectral efficiency (SE) and user fairness feature of non-orthogonal multiple access (NOMA) systems are achieved by exploiting user clustering (UC) more efficiently. However, a random UC certainly results in a suboptimal solution while an exhaustive search method comes at the cost of high complexity, especially for systems of medium-to-large size. To address this problem, we develop two efficient unsupervised machine learning (ML) based UC algorithms, namely k-means++ and improved k-means++, to effectively cluster users into disjoint clusters in cell-free massive multiple-input multiple-output (CFmMIMO) system. Using full-pilot zero-forcing at access points, we derive the sum SE in closed-form expression taking into account the impact of intra-cluster pilot contamination, inter-cluster interference, and imperfect successive interference cancellation. To comprehensively assess the system performance, we formulate the sum SE optimization problem, and then develop a simple yet efficient iterative algorithm for its solution. In addition, the performance of collocated massive MIMO-NOMA (COmMIMO-NOMA) system is also characterized. Numerical results are provided to show the superior performance of the proposed UC algorithms compared to other baseline schemes. The effectiveness of applying NOMA in CFmMIMO and COmMIMO systems is also validated.

[1]  Emil Björnson,et al.  Channel Hardening and Favorable Propagation in Cell-Free Massive MIMO With Stochastic Geometry , 2017, IEEE Transactions on Communications.

[2]  Andreas Krause,et al.  Approximate K-Means++ in Sublinear Time , 2016, AAAI.

[3]  Anil K. Jain Data clustering: 50 years beyond K-means , 2008, Pattern Recognit. Lett..

[4]  Amir Beck,et al.  A sequential parametric convex approximation method with applications to nonconvex truss topology design problems , 2010, J. Glob. Optim..

[5]  Alister G. Burr,et al.  On the Uplink Max–Min SINR of Cell-Free Massive MIMO Systems , 2019, IEEE Transactions on Wireless Communications.

[6]  Erik G. Larsson,et al.  Massive Access for 5G and Beyond , 2020, IEEE Journal on Selected Areas in Communications.

[7]  Yao Zhang,et al.  Spectral Efficiency Maximization for Uplink Cell-Free Massive MIMO-NOMA Networks , 2019, 2019 IEEE International Conference on Communications Workshops (ICC Workshops).

[8]  Sami Sieranoja,et al.  How much can k-means be improved by using better initialization and repeats? , 2019, Pattern Recognit..

[9]  Octavia A. Dobre,et al.  Joint Power Control and User Association for NOMA-Based Full-Duplex Systems , 2019, IEEE Transactions on Communications.

[10]  Octavia A. Dobre,et al.  Power-Domain Non-Orthogonal Multiple Access (NOMA) in 5G Systems: Potentials and Challenges , 2016, IEEE Communications Surveys & Tutorials.

[11]  Alister G. Burr,et al.  On the Performance of Cell-Free Massive MIMO Relying on Adaptive NOMA/OMA Mode-Switching , 2020, IEEE Transactions on Communications.

[12]  Hao Jiang,et al.  Cluster-based geometrical dynamic stochastic model for MIMO scattering channels , 2017, 2017 9th International Conference on Wireless Communications and Signal Processing (WCSP).

[13]  Octavia A. Dobre,et al.  Resource Allocation for Downlink NOMA Systems: Key Techniques and Open Issues , 2017, IEEE Wireless Communications.

[14]  Octavia A. Dobre,et al.  Semi-Blind Interference Aligned NOMA for Downlink MU-MISO Systems , 2020, IEEE Transactions on Communications.

[15]  H. Vincent Poor,et al.  Precoder Design for Signal Superposition in MIMO-NOMA Multicell Networks , 2017, IEEE Journal on Selected Areas in Communications.

[16]  Bhaskar D. Rao,et al.  Precoding and Power Optimization in Cell-Free Massive MIMO Systems , 2017, IEEE Transactions on Wireless Communications.

[17]  Naofal Al-Dhahir,et al.  Unsupervised Machine Learning-Based User Clustering in Millimeter-Wave-NOMA Systems , 2018, IEEE Transactions on Wireless Communications.

[18]  Octavia A. Dobre,et al.  On the Spectral and Energy Efficiencies of Full-Duplex Cell-Free Massive MIMO , 2020, IEEE Journal on Selected Areas in Communications.

[19]  Md. Farhad Hossain,et al.  An Architecture for M2M Communications Over Cellular Networks Using Clustering and Hybrid TDMA-NOMA , 2018, 2018 6th International Conference on Information and Communication Technology (ICoICT).

[20]  Antonia Maria Tulino,et al.  Random Matrix Theory and Wireless Communications , 2004, Found. Trends Commun. Inf. Theory.

[21]  Chintha Tellambura,et al.  Underlaid Spectrum Sharing for Cell-Free Massive MIMO-NOMA , 2020, IEEE Communications Letters.

[22]  Emil Björnson,et al.  Downlink Spectral Efficiency of Cell-Free Massive MIMO with Full-Pilot Zero-Forcing , 2018, 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[23]  Ali Reza Heidarpour,et al.  Rate Analysis of Cell-Free Massive MIMO-NOMA With Three Linear Precoders , 2019, IEEE Transactions on Communications.

[24]  Guillem Femenias,et al.  Clustered Cell-Free Massive MIMO , 2018, 2018 IEEE Globecom Workshops (GC Wkshps).

[25]  Erik G. Larsson,et al.  On the Total Energy Efficiency of Cell-Free Massive MIMO , 2017, IEEE Transactions on Green Communications and Networking.

[26]  Erik G. Larsson,et al.  Cell-Free Massive MIMO Versus Small Cells , 2016, IEEE Transactions on Wireless Communications.

[27]  Ke Gong,et al.  Mobile propagation loss with a low base station antenna for NLOS street microcells in urban area , 2001, IEEE VTS 53rd Vehicular Technology Conference, Spring 2001. Proceedings (Cat. No.01CH37202).

[28]  Yikai Li,et al.  NOMA-Aided Cell-Free Massive MIMO Systems , 2018, IEEE Wireless Communications Letters.

[29]  Jos F. Sturm,et al.  A Matlab toolbox for optimization over symmetric cones , 1999 .

[30]  Jian Yu,et al.  A Kernel-Power-Density-Based Algorithm for Channel Multipath Components Clustering , 2017, IEEE Transactions on Wireless Communications.

[31]  Gordon P. Wright,et al.  Technical Note - A General Inner Approximation Algorithm for Nonconvex Mathematical Programs , 1978, Oper. Res..

[32]  Aurélien Géron,et al.  Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems , 2017 .

[33]  Sergei Vassilvitskii,et al.  k-means++: the advantages of careful seeding , 2007, SODA '07.

[34]  Xiaochen Xia,et al.  Exploiting the Clustered Sparsity for Channel Estimation in Hybrid Analog-Digital Massive MIMO Systems , 2019, IEEE Access.

[35]  Huiling Jiang,et al.  System-level performance of downlink NOMA combined with SU-MIMO for future LTE enhancements , 2014, 2014 IEEE Globecom Workshops (GC Wkshps).

[36]  Rein Vesilo,et al.  An Enhanced K-means Clustering Algorithm with Non-Orthogonal Multiple Access (NOMA) for MMC Networks , 2018, 2018 28th International Telecommunication Networks and Applications Conference (ITNAC).