Adaptive Successive Interference Cancellation using Deep Learning for High Altitude Platform Station in Various K-Rician Channel

This research proposed the Adaptive-Successive Interference Cancellation (ASIC) method, which enlisted the performance and power efficiency from Successive Interference Cancellation (SIC) conventional. We employed deep learning as new technology for wireless communications. We have simulated for High Altitude Platform System (HAPS) communication using the Power Domain-Non-Orthogonal Multiple Access (PDNOMA) method for three Ground Stations (GS). We consider three different areas with the various K-Rician channel model on low, medium, and high elevation for analysis. To compare ASIC and SIC performance, we used the Signal-To-Noise Ratio (SNR) and Bit Error Rate (BER) as performance parameters. From the results of extensive research, we prove that ASIC performance is more efficient at the SNR value around 48.21%, 30.27%, and 42.85% in low, medium, and high elevation, respectively.