Incremental augmented affine projection algorithm for collaborative processing of complex signals

In this paper we propose a distributed and adaptive algorithm for collaborative processing of the complex signals. The proposed algorithm, which will be referred to as the incremental augmented affine projection algorithm (IncAAPA), not only utilizes the full second order statistical information in complex domain but also exploits the spatial diversity which is provided by the distribution of the nodes in the field. Moreover, since nodes are equipped with affine projection learning rules, they are able to track the variations in statistical information.

To derive the IncAAPA algorithm, we firstly formulate the estimation problem as a constrained optimization problem. Then we provide a solution for the problem which is amenable to distributed implementation. The proposed algorithm outperforms the noncooperative solution in terms of convergence rate and steady-state error. We present some simulations to evaluate the performance of the proposed algorithm.