Unsupervised Learning Algorithm for Intelligent Coverage Planning and Performance Optimization of Multitier Heterogeneous Network

Abstract

The densification of mobile network infrastructure has been widely used to increase the overall capacity and improve user experience. Additional tiers of small cells provide a tremendous increase in the spectrum reuse factor, which allows the allocation of more bandwidth per user equipment (UE). However, the effective utilization of this tremendous capacity is a challenging task due to numerous problems, including co-channel interference, nonuniform traffic demand within the coverage area, and energy efficiency. Existing solutions for these problems, such as stochastic geometry, cause excessive sensitivity to the pattern of the UE traffic demand. In this paper, we propose an intelligent solution for both coverage planning and performance optimization using unsupervised self-organizing map (SOM) learning. We use a combination of two different mobility patterns based on Bézier curves and Lévy flights for more natural UE mobility patterns compared with a conventional random point process. The proposed approach provides the advantage of adjusting the positions of the small cells based on an SOM, which maximizes the key performance indicators, such as average throughput, fairness, and coverage probability, in an unsupervised manner. Simulation results confirm that the proposed unsupervised SOM algorithm outperforms the conventional binomial point process for all simulated scenarios by up to 30% in average throughput and fairness and has an up to 6-dB greater signal-to-interference-plus-noise ratio perceived by the UEs.