Estimating CSI for Future Generation MIMO Networks Using Deep Learning Techniques and its Applicability to Varied Environments
Massive Multiple-Input Multiple-Output (MIMO) approach consists of high potential to achieve high data rate and one of the most favourable method to exploit channel feedback efficiency. Thus, a deep learning-based CSI feedback mechanism is proposed in this article to ensure high channel estimation efficiency with minimum CSI feedback overhead. Along with that, auto-encoders are adopted to study low dimensional representation of varied data structures. Moreover, CSI matrices are compressed at encoder side and recovered CSI matrices are obtained at decoder side. Further, convolution layers are utilized to get high quality features and fully linked layer is utilized to compress dimensions in CSI feedback matrices. The CSI feedback efficiency is enhanced using 𝐃𝐮𝐚𝐥𝐍𝐞𝐭−𝐍𝐂𝐂 Architecture by exploiting magnitude correlation between downlink and uplink medium. Here, data of two varied environments such as indoor and outdoor cellular environment considering the Cost 2100 database is utilized and simulation is performed in cloud platform. An investigation is carried out to compare performance results of proposed DLAE model in terms of NMSE and correlation efficiency against varied traditional channel estimation approaches. Performance results shows higher channel estimation accuracy and spectral efficiency enhancement.