Regular combining of cooperative and non-cooperative schemes for mitigation of the effect of noisy links in diffusion LMS adaptive networks

One of the problems encountered in wireless sensor networks is the effect of noisy links. So, in this paper we propose a new adaptive estimation algorithm that mitigates the effect of noisy links in diffusion least mean square (DLMS) adaptive networks. Our proposed algorithm is based on combining the cooperative and non-cooperative schemes, but this combination is done in a regular manner. Using this idea, we can benefit the cooperation advantage, and at the same time mitigate the effect of noisy links. Simulation results show that our proposed algorithm overrides the performance of the other algorithms proposed for this purpose.