基于机器学习方法的高速信道建模研究

随着高速信道的传输速率变快,传输长度变长,结构复杂度变高,对信道进行建模也变得复杂与艰难.将目前比较火热的机器学习方法与高速信道结合起来,提出了一个新颖的方法.利用采集的大量模拟数据,采用深度神经网络DN N与循环神经网络RN N对信道建模,模型一旦训练成功,就可以通过该仿真模型预测输出信号的眼图,快速精准地对信号完整...

High speed channel modeling based on machine learning

With the increase of transmission rate, transmission length and structure complexity of high-speed channel, channel modeling technology becomes more complex and difficult. This paper proposes a novel method by combining the popular machine learning method with high-speed channel. A large number of analog data are collected, and deep neural network (DNN) and recurrent neural network (RNN) methods are used to model the channel. Once the model is trained successfully, the eye diagram of the output signal can be predicted by the simulation model, and the signal integrity can be evaluated and analyzed quickly and accurately. In addition, in the high-speed channel, the serious interference and attenuation of the signal limits the transmission distance and transmission rate, which brings difficulties to the test and information collection. In order to recover the ideal signal, the high-speed serial link usually contains complex equalization blocks.The least mean square (LMS) algorithm is adopted to effectively eliminate the interference, reduce the bit error rate and improve the transmission rate.