A Machine-Learning Approach for the Exemplar Extraction of mmWave Industrial Wireless Channels

Industrial wireless channel modeling is essential for the development of industrial internet things (IIoT) systems. Moreover, millimeter-wave (mmWave) bands have a high potential to be used IIoT applications because their data-rates and better applicability having multiple antennas. As result, we introduce an exemplar extraction approach applied on mmWave measurements. A machine learning (ML) clustering scheme divide measured power-angle-delay-profiles into number groups with respect angle arrival. Each represented by power-delay-profile (PDP) provide tractable way testing evaluation systems through compactly representing different based spatial characteristics. Hence, communications equipment can performed over exemplars assess performance significantly reduced amount data, allowing lab-based device in realistic, yet repeatable, test environment. Governing equations are provided sufficient detail users implement technique own labs.