Abstract
Background & Objective: 5G Millimeter Wave (mmWave) Communication System is emerging as an upcoming commercial version of wireless communication for worldwide users. 5G mmWave Communication System can provide high data rates in the range of Gbps for many users simultaneously. This research work presents vegetation attenuation control in 5G mmWave communication system using software defined radio (SDR). In the SDR based 5G transmitter, the vegetation attenuation is calculated for the FCC recommended frequencies by using machine learning (ML). The proposed 5G ML transmitter system keeps learning mmWave propagation vegetation attenuation values for the mmWave frequencies along with the depth of vegetation by using supervised ML. The ML unit predicts the vegetation attenuation values using a regression model with the algorithms like KNearest Neighbors, Decision Tree and Random Forest.
Conclusion: Further, the 5G SDR transmitter calculates the Shannon channel capacity (SCC) for the selected frequencies by having ML unit generated vegetation attenuation values to maintain the desired transmission data rates. Vegetation attenuation and SCC are calculated for Delhi Technological University (DTU), New Delhi, India based location as DTU has high vegetation density.
Keywords: Machine Learning (ML), Millimeter Wave (mmWave), Shannon Channel Capacity (SCC), Software Defined Radio (SDR), communication system, transmitter.
Graphical Abstract