An improved variable step-size NLMS algorithm based on a Versiera function

In this paper, an improved variable step-size NLMS algorithm is proposed, which variable step-size scheme is designed by a Versiera function. The update of the step-size is subtly sensitive to the system noise due to employ the system input power and cross-correlation between the input signal and estimated error. Moreover, the proposed algorithm is stable. Simulation results for system identification demonstrate that the proposed algorithm is superior to other existing algorithms in terms of convergence rate, steady-state MSD and tracking ability.