Modeling of Passive Intermodulation Distortion Using the Neural Networks and the Cubic Volterra Filter

Abstract

In this paper, modeling of the third-order passive intermodulation distortion (PIMD) caused by the downlink signal in the frequency division duplex (FDD) wireless communication system is developed with the Focused Time Delay Neural Network (FTDNN) and the cubic Volterra Filter (CVF). PIMD is an interference signal generated due to the nonlinearity of a passive element in a wireless communication environment, and degrades the noise level of a receiver, resulting in a deterioration of communication quality. Estimation and performance evaluation of the proposed approaches are investigated with measured PIMD signals and transmitted downlink signals. It is observed that both FTDNN and CVF are suitable for modeling non-linearity of the PIMD generation process. © 2019 IEEE.