Enhancing mmWave Wireless Network Capacity through Machine Learning for Beamforming- and Transmission Power Optimization

There is an increasing importance to reduce overall energy usage, especially in the realm of 5<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup> and 6<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup> Generation (5G, 6G) networks. To address this requirement, cutting-edge technologies such as Machine Learning (ML) and Artificial Intelligence (AI) have been integrated into the operation of 5G networks. As AI continues to progress rapidly and ML emerges as a significant subset, the integration of these innovations into 5G/6G infrastructures has become a significant area of exploration and study. This article explores how ML methods can optimize transmission power values for antennas with different transmit/receive patterns, ultimately enhancing the overall channel capacity. Essentially, we utilized ML techniques to determine the maximum channel capacity achievable by identifying the best both, the best beamforming steering vectors (for both transmitters and receivers) and determine the optimal transmit power values for transmitters. This approach aims to enhance the efficiency and performance of 5G/6G networks while minimizing energy consumption.