Power System State Forecasting Using Regression Analysis

This paper presents a block-diagonal state transition matrix based on regression analysis. The state transition matrix is used to forecast the system state, which is subsequently corrected through extended Kalman filter in classical dynamic state estimation (DSE). The transition matrix is updated when new online measurement data are available. The forecasting accuracy can be traded off according to the frequency of the updates. The tests on IEEE 14- and 30-bus system show improvement in the state forecasting accuracy when compared to the existing state forecasting methods in dynamic state estimation.