Fast State Estimation of Power System based on Extreme Learning Machine Pseudo-Measurement Modeling

Abstract

Hybrid measurement of the phasor measurement units (PMU) and the supervisory control and data acquisition (SCADA) system is used for state estimation of power transmission system when PMU deployment can not cover all buses. The traditional iterative solution process of state estimation is low efficient and may cause truncation error. A fast state estimation method based on pseudo-measurement modeling of extreme learning machine (ELM) for power transmission system state estimation is proposed. The injected powers measured by SCADA are used as input, the real and imaginary parts of bus voltages are used as output. The pseudo-measurement value model and pseudo-measurement error model are trained using historical data. In the new time, the pseudo-measurements obtained from the trained model are combined with the PMU measurements for fast linear state estimation. The final state estimation results can be obtained quickly. Simulation results of IEEE 14 system show that the proposed method not only improves the accuracy of state estimation, but also greatly reduces the calculation time. It can provide basic information for other applications in EMS accurately and quickly.