Decentralized estimation: an indirect method

Presents an indirect method for decentralized estimation of interconnected large scale systems. The estimators are obtained in two steps: an approximate model for the desired local variables, using optimal aggregation techniques, is derived in the first step and in the second step a local filter is derived using the model obtained in the first step and local measurements. Kalman filtering and H-/spl infin/ filtering methods are the means of obtaining decentralized estimators.