Unsupervised Clustering for Nonlinear Equalization in Indoor Millimeter-Wave Communications

Abstract

Millimeter-wave (mmWave) systems have been considered as a promising candidate for 5G networks because of their potential advances in significant bandwidth enhancement. However, due to the extremely high operating frequency of mmWave systems, they generally suffer from severe frequencyselective propagation and nonlinear distortion in the power amplifier, which introduces unfavorable impact on the signal detection process. We discover that for indoor mmWave communications, the constellation of signals becomes much more ''clean and tidy'' at the receiver side compared with the current wireless systems (e.g., LTE and WiFi), thanks to the channel sparsity characteristic of mmWave communications. Motivated by this observation, we propose in this paper several detection algorithms. Specifically, K-means clustering (KMC) algorithm is first introduced into clustering signal detection due to its advantage in the circle or spherical cluster shape. Then, an improved KMC detector is proposed to avoid the deficiencies of KMC for the error floor and high complexity. Moreover, a density and distance-based clustering detector, a non-iterative algorithm, is proposed and it does not need to preset the number of clusters. The aboveproposed algorithms do not require any prior information about the power amplifier and the channel state information at the receiver end, which presents noticeable practical achievements on cost, complexity, and hardware constraints. The simulation results verify the effectiveness of the proposed schemes.INDEX TERMS Millimeter-wave (mmWave) communication, nonlinear signal detection, nonlinear power amplifier, unsupervised clustering.

A Comprehensive Review on Artificial Intelligence/Machine Learning Algorithms for Empowering the Future IoT Toward 6G Era

“…Non-linear equalization in wireless networks has received massive interest for signal detection. Unsupervised learning based non-linear equalization studied in [107] uses K-means clustering which does not require CSI and power amplifier related information. This helps in achieving hardware constraints, system complexity and cost.…”

“…Research topic Research analysis/findings K-means clustering [103] Joint resource allocation and clustering mechanisms Energy efficiency analysis [104] Routing protocol with K-means clustering, maximum stable set problem and continuous hopfield network Improved throughput, transmission delay reduction and cluster stability [105] Routing algorithm Data transmission rate analysis and energy utilization [106] Edge computing node deployment mechanism Analysis of computing resources deployment cost and network delay tradeoff with proposed mechanism and comparison of that against traditional K-means clustering and random deployment method [107] Non-linear equalization operation Performance evaluation in terms of computational complexity, cost and hardware constraints [108] Device clustering scheme Improved packet delivery ratio and latency compared to ACO and GWO [109] Unequal clustering mechanism Transmission delay and energy consumption reduction with proposed algorithm and comparison of that against withEKMT, UCR and CU-CRA" [110] Device clustering scheme Comparison of energy utilization against low-energy adaptive clustering hierarchy (LEACH) based approaches [111] Device clustering scheme Analysis of energy consumption balancing with the proposed scheme [112] Device clustering scheme Analysis of network coverage and energy utilization tradeoff [113] Device clustering scheme Analysis of transmission delay reduction and protection from malicious device induced attacks [114] Data clustering Immunity from DoS attacks Expectation Maximization [115] Aerial base station deployment with proposed EM based approach Improved downlink capacity, low energy consumption and service delay against traditional EM and K-means approach [116] Indoor localization Performance evaluation of the localization method [117] Indoor localization Performance evaluation against KNN in terms of localization errors [118] Time difference of arrival (TDOA) source direct position determination Reduction of computational load of the direct position determination [119] Passive localization scheme Analysis of the localization performance, computational complexity and communication overhead [120] Mulltitarget localization scheme Localization error analysis with the proposed method, basis pursuit, GMP and least square compressive sensing [121] RIS channel modeling Outrage probability analysis for the proposed approach [122] Channel characterization method Performance analysis in terms of RMS delay, AOA and ZOA spread [123...…”