Deep Learning Based Pilot Assisted Channel Estimation for Rician Fading Massive MIMO Uplink Communication System

Abstract

Massive multiple input multiple output (MIMO) communication is one of the promising candidates for the successful deployment of Fifth-generation communication which offers an extensive improvement in spectral efficiency as well as data rate. The estimation of massive MIMO channel is very arduous due to its enormous diversity gain and enlarged capacity. However, channel estimation for uplink Rician fading massive MIMO system, where the channel is occupied with both Line of sight and non-line of sight component is not properly investigated yet. In this article, we have studied deep learning based channel estimation scheme for the massive MIMO system in Rician fading environment. Unlike the traditional approach, we have developed an optimized neural network model which can intelligently design pilot and estimate channels. We have simulated massive MIMO system at different signal to noise ratio values varying number of transmitted antennas and also investigated the performance of our proposed scheme by analyzing simulation results.