Deep graph neural network optimized with fertile field algorithm based detection model for uplink multiuser massive multiple‐input and multiple‐output system

Abstract

AbstractThe core requirements are generated for sixth generation (6G) wireless communication with low‐latency and ultra‐high speeds to increase the count of ultra scale intelligent factors, like smart cars, mobile root users. The advancement of 6G communication can lead the interference exploitation. To manage the exploitation of uplink multiuser massive (UMM), the multiple‐input and multiple‐output (MIMO) is very difficult to detect the mechanisms, particularly, quadrature amplitude modulation (QAM) signals. To overcome these issues, a novel deep graph neural network optimized with fertile field algorithm based detection model (DGNNO‐FFA) is proposed in this article for uplink multiuser massive MIMO System. The proposed DGNNO‐FFA approach minimizes the channel estimation errors under low signal to noise ratio (SNR) with better bit error rate (BER). Finally, the proposed DGNNO‐FFA approach attains 11.02%, 12.22%, and 25.27% lower BER value, 14.55%, 18.66%, and 29.49% higher energy efficiency, 15.59%, 19.06%, and 29.59% lower NMSE, and 15.59%, 19.06%, and 29.59% lower computational complexity compared with other existing approaches, like deep neural network based semi definite relaxation (DNN‐SDR), QR based zero forcing algorithms (QR‐ZF), and QAM based 2‐dimensional double successive projection model (QAM‐2D‐DSP).