.png){kind=icon}
返回
Incremental Model Evolution for Power System Security Early Warning Based on Knowledge Distillation and Active Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TII.2024.3431034.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
Keyword:
Active learning
catastrophic forgetting
knowledge distillation
power system security
renewable power
Active learning
catastrophic forgetting
knowledge distillation
power system security
renewable power
期刊
IF:
9.9
论文数:
8.6K
被引数:
6.0W
机构
引用论文
Conditional Style-Based Generative Adversarial Networks for Renewable Scenario Generation用于可再生场景生成的基于条件样式的生成对抗网络
PREAI
分享收藏Robust stochastic optimal dispatching method of multi-energy virtual power plant considering multiple uncertainties考虑多不确定性的多能源虚拟电厂鲁棒随机优化调度方法.png)
APPLIED ENERGY
APPLIED ENERGYIF11
PREAI
分享收藏Intelligent Early Warning of Power System Dynamic Insecurity Risk: Toward Optimal Accuracy-Earliness Tradeoff电力系统动态不安全风险的智能预警: 走向最佳精度-早期权衡
PREAI
分享收藏KDnet-RUL: A Knowledge Distillation Framework to Compress Deep Neural Networks for Machine Remaining Useful Life PredictionKdnet-rul: 压缩深度神经网络用于机器剩余使用寿命预测的知识蒸馏框架
PREAI
分享收藏
查看更多内容