Increasing the Initial Convergence of Distributed Diffusion LMS Algorithm by a New Variable Tap-Length Variable Step-Size Method

Among strategies using in distributed adaptive networks diffusion based algorithms despite their scalability, robustness and steady state performance suffer from slow initialconvergence. We propose a method to speed up this convergence rate by arranging the network nodes intosubgroups, partitioning the tap weight vector and takingadvantage of the larger step-size allowed for short filters. As our simulation results show, the proposed algorithm has afaster convergence rate as compared with conventional diffusion LMS algorithm and other algorithms have intended toincrease the initial convergence rate of diffusion algorithms

کلیدواژه ها:

Distributed estimation ، diffusion ، initial convergence ، LMS algorithm