Single-Step Allowable Action Threshold Determination of Renewable Energy Automatic Generation Control Using Model-Based and Data-Driven Method

Renewable energy automatic generation control (AGC) has the characteristics of rapid adjustment and flexibility, which play a critical role in frequency regulation. Abnormal outputs in renewable energy AGC may trigger frequency fluctuations and threaten grid security. To address the above problems in renewable energy, AGC, a combined model-based and data-driven method for determining the single-step allowable action threshold, is proposed. Firstly, an AGC model with multiple frequency-regulating units is built, and the threshold can be obtained through simulation considering system status parameters. Secondly, as the model-based method struggles to satisfy the requirement of rapidity, a data-driven model based on CNN-LSTM is employed to determine the threshold in real-time. The training data is provided by a model-based method. Considering the limited coverage and interpretability of neural networks, a statistical error-prevention method is proposed to avoid deviations. Then, an adaptive piecewise constant approximation algorithm is employezd to reduce threshold update frequency and the burden for dispatchers. Finally, an adaptive threshold adjustment method for extreme scenarios is proposed, ensuring the frequency regulation of renewable energy AGC under extreme scenarios. Through experiments, the reliability and validity of the proposed method in threshold determination and error prevention are validated.