Hierarchical dynamic state estimator using ANN-based dynamic load prediction

The paper presents a new scheme for dynamic state estimation in power systems. The dynamics of the power system are modelled more realistically using artificial-neural-network-based bus-load prediction and load flow for state prediction. At the filtering step a hierarchical model which incorporates the measurement function nonlinearities is used. This considerably reduces the computational effort, making the proposed scheme suitable for on-line application. Test results for IEEE 118-bus test system are presented to show the characteristics of the present method.