一种变步长LMS算法自适应均衡器研究

Study on Adaptive Channel Equalizer based on Variable Step-size LMS Algorithm

最小均方(LMS,Least Mean Square)算法由于其简单易实现,在自适应信号处理领域十分流行且应用广泛,但其缺点是收敛速度相当缓慢。研究了基于一种变步长(VSS,Variable Step Size)LMS算法的自适应信道均衡器。仿真了LMS算法和VSS-LMS算法的迭代收敛过程和对加噪正弦信号的处理。结果表明,跟传统LMS算法相比,这种变步长的LMS算法在收敛性能上有显著的优势。

LMS, for its low complexity, is very popular and widely used in the field of adaptive signal processing, while is very slow in convergency. An adaptive channel equalizer based on variable step-size LMS （VSS LMS） algorithm is described in this paper. Simulation on the interative converging process and the processing of sine signal with noise shows that compared with LMS, VSS-LMS is of fairly better convergency performance.