An Improved Diffusion Affine Projection Estimation Algorithm for Wireless Sensor Networks

Affine projection algorithms have shown robustness against highly correlated input signals. To make the affine projection algorithm applicable for parameter estimation in wireless sensor networks, this work proposed a novel distributed affine projection algorithm by using the adapt-then-combine (ATC) scheme of the diffusion strategy. However, poorly performing nodes can potentially degrade to estimation performance. Thus, we develop an improved ATC diffusion affine projection algorithm (improved ATC-dAPA) with adaptive node selection to maintain the estimation accuracy. The mean and mean square deviation of the proposed algorithm are analyzed. The numerical simulation results illustrate that the proposed algorithm can achieve more accurate estimations than several related algorithms.