Abstract:

In order to avoid the conflict between convergence speed and stable state error, and improve the adaptive filter algorithm, a new variable step-size convexcombination of least mean square (NVS-CLMS) algorithm is proposed by using the improved Lorentzian function. The new algorithm effectively improves convergence rate and has good anti-interference performance. Furthermore, the instantaneous transfer scheme is utilized to overcome disadvantages of CLMS and the sign function in iterative of the parameter can also reduce the computational complexity. Theoretical analysis and simulation results show that under different environments, the proposed algorithm, compared with the CLMS and VS-CLMS algorithms, not only has a superior capability of tracking, but also can maintain a better convergence.