A least square approach for distributed sensor fusion in bandwidth-constrained sensor networks

In this paper, we consider a simple model of distributed sensor fusion problem in sensor networks with asymmetric links, where the common goal is linear parameter estimation. For the realistic scenario of bandwidth-constrained networks, we propose a least square approach, based on distributed quantized consensus algorithms, to compute the ideal centralized sample mean estimate. Analytical results show that the proposed approach is effective in smearing out the quantization errors, and outperforms the centralized approaches with respect to the estimation performance. Simulation results are provided to validate the analytical results.