Massive MIMO Signal Detection Based on Interference Cancellation Assisted Sparsely Connected Neural Network br

In recent years, deep learning has become one of the key technologies in the field of wirelesscommunication. In a series of MIMO signal detection algorithms based on deep learning, most of them do notfully consider the interference cancellation problem between adjacent antennas, hence the impact of multi-userinterference on the bit error rate performance can not be completely eliminated. To this end, a method thatcombines deep learning and Successive Interference Cancellation (SIC) algorithms for uplink signal detection ina massive MIMO system is propesed. Firstly, by optimizing the traditional Detection Network (DetNet) andimproving the ScNet (Sparsely connected neural Network), a detection algorithm based on the Deep NeuralNetwork (DNN), called Improved ScNet (ImpScNet), is proposed. On this basis, the SIC is applied to thedesign of the deep learning framework structure, and a massive MIMO multi-user SIC detection algorithmbased on deep learning is proposed, which is called ImpScNet-SIC. This algorithm is divided into two stages oneach detection layer. The first stage is provided by the ImpScNet algorithm proposed in this paper to providethe initial solution, and then the initial solution is demodulated to the corresponding constellation point as theinput of the SIC, which constitutes the second stage. In addition, the ImpScNet algorithm is also used in SIC toestimate the transmitted symbols in order to obtain the best performance. Simulation results show that,compared with various typical representative algorithms, the ImpScNet-SIC detection algorithm proposed inthis paper is particularly suitable for the massive MIMO signal detection. It has the advantages of fastconvergence speed, stable convergence and relatively low complexity. And there is at least 0.5 dB gain in 10-3 bit error rate