The issue considered in the current study is the problem of adaptive distributedestimation based on diffusion strategy which can exploit sparsity in improving estimation error and reducing communications. It has been...
详细信息
The issue considered in the current study is the problem of adaptive distributedestimation based on diffusion strategy which can exploit sparsity in improving estimation error and reducing communications. It has been shown that distributedestimation leads to a good performance in terms of the error value, convergence rate, and robustness against node and link failures in wireless sensor networks. However, the main focus of many works in the field of distributedestimation research is on convergence speed and estimation error, neglecting the fact that communications among the nodes require a lot of transmissions. In this work, the focus is on a solution based on sparsediffusion least mean squares (LMS) algorithm, and a new version of sparsediffusion LMS algorithm is proposed which takes both communications and error cost into account. Also, the computation complexity and communication cost for every node of the network, as well as performance analysis of the proposed strategy, is provided. The performance of the proposed method in comparison with the existing methods is illustrated by means of simulations in terms of computational and communicational cost, and flexibility to signal changes.
暂无评论