Model-Data Integration Driven Based Power System Frequency Response Model

The power system frequency response models based on model-driven or data-driven methods have contradictions between calculation speed, accuracy, and result interpretability. Considering the strengths and disadvantages of various models in the real-time application, a model-data integration driven method is proposed. The method uses System Frequency Response (SFR) model to predict the frequency response dynamic process and uses Extreme Learning Machine (ELM) Optimized by Particle Swarm Optimization (ELM) model to correct the error of the predicted results. It can greatly improve calculation accuracy while keeping a high calculation speed. Moreover, the model-data integration driven method is less dependent on the sample data to improve the interpretability of the calculation results. The simulation on the WSCC 9-bus system verifies that the method can quickly and accurately calculate the dynamic process of frequency response after a large-scale disturbance, and has a good generalization ability. It can further provide an emergency assistance decision for the dispatching and control of the power system to prevent the frequency crash.