Machine Learning in Downlink Coordinated Multipoint in Heterogeneous Networks

We propose a method for practical downlink coordinated multipoint (DL CoMP) implementation in the fifth generation of wireless communications (5G) also known as New Radio (NR). We base our method on supervised machine learning. Contributions of this paper are to 1) demonstrate that a support vector machine (SVM) classifier can learn improved conditions at which DL CoMP can be dynamically triggered in a scalable realistic environment and 2) increase user throughput in a heterogeneous network as a result of learning improved triggering conditions of CoMP. Our simulation results show an improvement in both the macro and pico base station peak throughputs due to the informed triggering of the multiple DL CoMP radio streams as learned from the SVM classifier.