ABSTRACT
This chapter is devoted to the development of wireless estimation methods as distinct applications of wireless sensor networks. It is known that the usage of WSNs for state-estimation has recently gained increasing attention due to its cost effectiveness and feasibility. One of the major challenges of state-estimation via WSNs is the distribution of the centralized state-estimator among the nodes in the network. Significant emphasis has been on developing non-centralized stateestimators considering communication, processing-demand and estimation-error.
State-estimation is a widely used technique in monitoring and control applications. The method requires that all process-measurements are sent to a central system which estimates the global state-vector of the process. The interest in using WSNs to retrieve the measurements has recently grown [394], due to improved performance and feasibility in new application areas. However, for WSNs consisting of a large amount of nodes a central state-estimator becomes impracticable due to high processing demand and energy consumption. As a result, the distribution of the centralized Kalman filter, in which each node estimates its own state-vector, has become a challenging and active research area.
