Inter-Cell Interference Suppression For Mimo-Ofdm Systems Based On Complex-Valued Neural Network

In theory, complex-valued neural network (CVNN) is more suitable for processing complex signals. In this paper, we propose an effective complex-valued neural network structure based on the traditional interference rejection combining (IRC) algorithm to suppress the inter-cell interference in MIMO-OFDM systems. The proposed CVNN has small size and supports fast convergence within several pilot symbols in resource blocks (RBs), which can meet the real-time requirements in practical application scenarios. Numerical results based on standardized channels and measured channels show that the proposed method outperforms the traditional interference suppression algorithms and requires comparable computational complexity.