中圖分類號(hào)： TN925 文獻(xiàn)標(biāo)識(shí)碼： A DOI：10.16157/j.issn.0258-7998.222520 中文引用格式： 曾相誌，申濱，陽(yáng)建. 基于SDNSR-Net深度網(wǎng)絡(luò)的大規(guī)模MIMO信號(hào)檢測(cè)算法[J].電子技術(shù)應(yīng)用，2022，48(11)：84-88. 英文引用格式： Zeng Xiangzhi，Shen Bin，Yang Jian. Signal detection based on SDNSR-Net deep network for massive MIMO systems[J]. Application of Electronic Technique，2022，48(11)：84-88.
Signal detection based on SDNSR-Net deep network for massive MIMO systems
Zeng Xiangzhi，Shen Bin，Yang Jian
School of Communication and Information Engineering，Chongqing University of Posts and Telecommunications， Chongqing 400065，China
Abstract： Massive multiple-input multiple-output(MIMO) systems can effectively improve the spectrum efficiency. When the antenna scale gradually tends to infinity, the minimum mean square error(MMSE) detection algorithm can achieve near-optimal detection performance. However, due to the matrix inversion required in the algorithm, which brings extremely high computational complexity, it is difficult to implement in a massive MIMO system. The Richardson algorithm can achieve the detection performance of the MMSE algorithm in an iterative form without matrix inversion, but the algorithm is greatly affected by its relaxation parameters. In the Richardson algorithm combined with the steepest gradient descent algorithm (SDNSR), the error of the relaxation parameter can be compensated by the gradient descent algorithm, but the computational complexity is increased. This paper firstly uses the idea of deep expansion to map the iterative process of SDNSR to a deep detection network (SDNSR-Net); then, by modifying the network structure and adding trainable parameters，the computational complexity is reduced and the detection accuracy is improved. The experimental results show that SDNSR-Net is superior to other typical detection algorithms in the case of different signal-to-noise ratios and antenna configurations in the uplink massive MIMO system and can be used as an effective detection scheme in practice.
Key words : massive MIMO system；signal detection；modern driven；deep learning
0 引言
大規(guī)模MIMO系統(tǒng)中存在信道硬化現(xiàn)象，即由信道矩陣生成的Gram矩陣的對(duì)角項(xiàng)遠(yuǎn)大于非對(duì)角項(xiàng)。在該情況下最小均方誤差(Minimum Mean Square Error，MMSE)檢測(cè)算法已證明可以達(dá)到次優(yōu)的檢測(cè)性能[1]。然而該算法中存在矩陣求逆運(yùn)算，因此難以適用于大規(guī)模MIMO系統(tǒng)。
為降低線性檢測(cè)算法的計(jì)算復(fù)雜度，出現(xiàn)了Richardson迭代[2]、Jacobi迭代[3]和逐次超松弛(Successive Over Relaxation，SOR)迭代[4]等迭代檢測(cè)算法。然而，在大規(guī)模MIMO系統(tǒng)中，隨著用戶增加，該類算法的檢測(cè)性能退化嚴(yán)重。
