Dynamic state estimation in power system based on integrated forecasting model and adaptive filter

This paper further analyzes dynamic state estimation theory based on the extend Kalman filter (EKF) and points out two existent problems. Then model and algorithm for self-adapting dynamic estimator is presented here. Their new ideas embody two aspects. In forecasting model, considering control action of nodal power to system states and self-regulation of states, integrated model for system states is used to increase prediction accuracy. In filtering model, using least square support vector machines (LSSVM) technology, self-adapting dynamic filter is formed with limited memory to increase estimation capability and computing speed. It makes a satisfying result in actual application for power system control center of Shandong province.