Online Prediction Method for Power System Frequency Response Analysis Based on Swarm Intelligence Fusion Model

Abstract

Instability at transient frequency caused by faults in complex power systems is one of the greatest threats to operational safety. By analyzing the frequency response of power system in real-time and adopting control strategies promptly, power system accidents can be efficiently prevented. While existing online analysis methods integrate physical-driven and data-driven methodologies, they do not effectively utilize frequency timing characteristics. Consequently, a swarm intelligence fusion model, which integrates physical-driven and data-driven methods, is proposed as an improved frequency response analysis method. The transient frequency affecting components are separated into primary state variables and system time series data based on the properties of the time sequence. To preserve the actual relationship of the electrical mechanism model, the system frequency response (SFR) model is used as the physical-driven method for the primary state variables of the system. The Long Short Term Memory (LSTM) network was used as the data-driven method to extract timing features and correct the SFR model's prediction using the system time series data as input. The two methods are combined using the bootstrap mode to form the fusion model, and the structure of the model is optimized using an improved sparrow search algorithm (ISSA), a swarm intelligence optimization algorithm. The model structure is adapted autonomously, implementing a method for online frequency response analysis. The simulation on the New England 39-bus system has verified that the method can quickly and accurately calculate the dynamic process of frequency response after a large-scale disturbance.INDEX TERMS Transient response prediction, integrated model, system frequency response, LSTM, improved sparrow search algorithm.

Review of Data-Driven Techniques for On-Line Static and Dynamic Security Assessment of Modern Power Systems

“…Several of the required data are not trivial to ascertain and/or calculate, e.g., load damping coefficients and generator governor response times. One approach also considers the output of a continuously calculated modeldriven system frequency response (SFR) value as input to the prediction [126]. Furthermore, the output of specific generation types and/or reserve capacity is often requested, suggesting that the trained models are very sensitive to the specific network configuration and operating conditions.…”

“…However, data of the type of disturbances analyzed was not discussed in detail in the paper. [126] also used an LSTM model, here in combination with a physical-based model of the system frequency response, to predict the system state. An alternative approach was developed in [117], which considered the impact of uncertainty in wind generation on frequency stability using a physics-guided gated recurrent unit (PG-GRU) neural network as the foundation of the frequency stability assessment.…”