Large-scale MIMO depth expansion precoding method and device based on conjugate gradient method

• Main Authors: SHI XUEPU, ZHAO CHUNMING, SHEN HONG, XU PANJUAN
• Format: Patent
• Language: Chinese; English
• Published: 23.06.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; PHYSICS; TRANSMISSION

The invention discloses a large-scale MIMO depth expansion precoding method and device based on a conjugate gradient method, and belongs to the field of wireless communication, and the method comprises the steps: obtaining a downlink air interface channel vector and a transmission vector; and inputting the downlink air interface channel vector and the transmission vector into a pre-trained nonlinear neural network to obtain a pre-coded transmission signal. The nonlinear neural network is obtained by combining a deep expansion multi-layer nonlinear sub-network taking step length in a conjugate gradient algorithm as a training parameter and a single-layer linear sub-network at a receiver taking a receiver coefficient as a training parameter, and training by using a downlink air interface channel vector and emission vector training set. An internal structure of a conjugate gradient MMSE precoding algorithm is combined with an advanced DNN network, a model-driven supervised neural network is constructed by using