Correction-Based Diffusion LMS Algorithms for Distributed Estimation

In this paper, we consider distributed estimation problems where a set of agents are used for jointly estimating an interesting parameter from the noise measurements. By using the adaptation-then-combination rule in the traditional diffusion least mean square (DLMS), a DLMS is proposed by introducing a correction step with a gain factor between the adaptation and combination steps. An explicit expression for the network mean-square deviation is derived for the proposed algorithm, and a sufficient condition is established to guarantee the mean stability. Simulation results are provided to verify theoretical results, and it is shown that the proposed algorithm outperforms the traditional DLMS.