数据模型协同驱动的MIMO系统性能预测方法  

Learnable Model-driven Performance Prediction for MIMO Systems

作　　者：张晓丹[1] 孟帆 张铖 刘升恒 黄永明 ZHANG Xiaodan;MENG Fan;ZHANG Cheng;LIU Shengheng;HUANG Yongming(Shenzhen Institute of Information Technology,Shenzhen,Guangdong 518172,China;Purple Mountain Laboratories,Nanjing,Jiangsu 211111,China;National Mobile Communications Research Laboratory,Southeast University,Nanjing,Jiangsu 210096,China)

机构地区：[1]深圳信息职业技术学院,广东深圳518172 [2]网络通信与安全紫金山实验室,江苏南京211111 [3]东南大学移动通信国家重点实验室,江苏南京210096

出　　处：《信号处理》2024年第7期1354-1367,共14页Journal of Signal Processing

基　　金：国家自然科学基金(62201394)。

摘　　要：在具有未知同频干扰和信道状态信息具有不确定性的复杂场景下,现有的多输入多输出系统的性能分析和优化方案通常会退化甚至失效。为了适应这些挑战并更好地完成网络自动调优任务,提出了一个通用的数据模型协同驱动框架,该框架是真实通信系统的数字孪生,系统性能指标由系统参数决定。为了解释所提出的框架是如何工作的,将正则化迫零预编码作为实例。该实例中,首先在模型驱动方面,使用确定性等同理论来获得系统的性能近似结果。但是,该近似结果仅在理想条件下成立,例如系统已知信道状态信息不确定度、无穷天线数和没有任何未知同频干扰。因此在数据驱动方面,使用神经网络以网络参数和近似结果为输入,来进一步推断更准确的系统性能。因为利用了模型数据双驱动方法,轻量级的神经网络具有很好的性能。数据模型双驱动的性能估计器也是该系统的数字孪生。基于该数字孪生,设计了一个信道不确定度估计的流程和算法,以快速感知信道不确定度来支持该系统的自适应优化。该流程中,系统首先以一个初始信道不确定度做信号传输,并获得系统性能指标的检测结果。随后,根据性能估计器,使用梯度投影法,以该检测结果来反推信道不确定度,纠正环境非理想因素。仿真结果验证了所提算法的有效性,该数据模型协同驱动框架对于复杂场景下多输入多输出系统的性能预测具有研究意义。Practical wireless communication systems are often complex and experience unknown cochannel interference and uncertainties in the channel state information(CSI).Existing performance analysis and optimization schemes for multiple-input multiple-output(MIMO)systems frequently degrade or even fail.To adapt to these challenges and perform better network auto-tuning,we propose a generic data-and model-driven,i.e.,dual-driven,framework,which is a digital twin of an actual MIMO communication system.We theoretically prove that the proposed dual-driven scheme has fewer training errors than the data-driven schemes based on the Lipschitz continuity condition.To explain the mecha-nism of the proposed framework works,we use regularized zero-forcing(RZF)precoding in an imperfect MIMO sys-tem as an example.The system performance is determined by system parameters.In this example,first,on the model driven side,deterministic equivalence theory is used to obtain an approximation result of the system performance indica-tors.However,the approximation result holds only under ideal conditions,e.g.,known CSI uncertainty of the system,infinite number of antennas,and absence of any unknown interference.Therefore,on the data-driven side,we propose the use of a neural network(NN)to further elicit a more accurate system performance.Specifically,the input of the NN includes the approximation results and system parameters,and the output is a refined estimation of the system perfor-mance indicators.Thus,the learned NN can inherently solve imperfect system problems.The proposed dual-driven per-formance estimator is also a digital twin of the actual system.Based on this digital twin,a channel uncertainty estima-tion flow and algorithm are designed to quickly sense the channel uncertainty to support adaptive optimization of this system.In this flow,the system first performs signaling with an initial channel uncertainty and obtains the detection re-sults of the performance metrics.Subsequently,the channel uncertainty is inverted with this detectio

关 键 词：智能无线通信 数字孪生 性能预测 信道状态信息 线性波束赋形 

分 类 号：TN929.5[电子电信—通信与信息系统]