Conjugate gradient large-scale MIMO detection method based on deep learning

Abstract

The invention provides a conjugate gradient large-scale MIMO detection method based on deep learning for signal detection for a large-scale MIMO system in which the number of transmitting antennas is greater than that of receiving antennas. According to the method, proper trainable parameters are selected, a CG iterative algorithm with the trainable parameters is expanded into a deep neural network, and optimal parameters of each layer are found through network training. And through an initial value iteration strategy based on characteristic value estimation, the convergence of the algorithm is improved. According to the method, rapid convergence during parameter estimation can be ensured. In addition, the number of trainable parameters is only related to the number of network layers and is not related to the number of antennas. The characteristics ensure the rapid and stable training process of the method and the reasonable expandability of a large-scale system. According to the invention, a lower bit error rate is achieved with lower complexity.

Description

technical field [0001] The invention relates to a deep learning-based conjugate gradient massive MIMO signal detection method, which belongs to the cross field of machine learning and MIMO signal detection. Background technique [0002] With the rapid development of network and information technology, massive MIMO technology has become one of the key technologies of the fifth-generation mobile communication system. Massive MIMO technology can configure a large number of antennas at the base station, serve multiple users at the same time, and effectively achieve capacity gain , spatial multiplexing gain and high spectral efficiency, to meet the needs of users in terms of wireless data transmission rate, has become a research hotspot in the field of communication. [0003] However, due to the increase in the number of antennas on the receiving side and the user side, the signals transmitted by the user are superimposed on the base station, resulting in interference between sig...

AI Technical Summary

Problems solved by technology

Approximation methods, such as the Neumann series expansion algorithm, can avoid directly inverting the matrix, but when the series expansion term is greater than 2, the complexity of the algorithm increases greatly; iterative algorithms, such as the continuous hyper-relaxation method, can be well Approximate the performance of the MMSE algorithm, but when the number of antennas at the receiving end and the transmitting end are similar, the performance of the algorithm is not good

Images