Incremental Model Evolution for Power System Security Early Warning Based on Knowledge Distillation and Active Learning

Security early warning is crucial for resisting power system risk. To deal with renewable uncertainty, offline trained early-warning models need to be evolved incrementally. Catastrophic forgetting is main obstacle of model evolution. With the evolution times of early-warning models increasing, the capability of existing methods to mitigate catastrophic forgetting gradually decreases. Knowledge distillation can transfer the learned knowledge from the previous model to the updated model. To mitigate catastrophic forgetting, an incremental model evolution method for security early warning based on knowledge distillation and active learning is proposed. First, an incremental style-based generative adversarial network is formulated to generate renewable power scenarios, which utilizes knowledge distillation to retain previously learned knowledge. An improved concept drift detection method is proposed to determine model evolution moment. Then, an incremental deep regression model based on stacked target-related denoising autoencoder and knowledge distillation is constructed to assess system security index. Finally, active learning is deployed to select informative new samples and solve the objective conflict problem of knowledge distillation. Simulation results of a provincial grid in China demonstrate that proposed method can constantly improve early warning accuracy and effectively retain knowledge learned by previous samples. The proposed method can improve the adaptability of early-warning models to actual power system operating conditions, which enhances the intelligence level of security analysis to copy with renewable uncertainty.