Energy-efficient distributed parameter estimation with partial updates

This paper presents an innovative approach to distributed estimation which features partial updates of parameter estimations, thereby offering significant reduction in energy consumption in the sensors. The proposed estimation scheme updates only a subset of the parameters at each iteration. This not only reduces data processing complexity, but also reduces the energy required for diffusing the parameter estimates. In distributed parameter estimation, sensor nodes consume energy not only in processing data, but most costly, in communicating and diffusing updated parameter estimates. Reducing the number of parameters to be updated and diffused are thus an effective way to save in energy consumption. As such, the most fruitful outcome in partial updates is saving in energy required to diffuse those updated parameter estimates. The proposed scheme is a viable alternative to conventional set-membership adaptive algorithms that feature data-dependent selective updates of parameter estimates.