Deep Active Learning for Solvability Prediction in Power Systems
This work addresses solvability prediction for power systems, offering a more efficient approach than passive methods, though it is incremental as it builds on existing machine learning techniques.
The authors tackled the problem of predicting power system solvability by proposing a deep active learning framework that selects informative instances to reduce labeled data needs, achieving significant reductions in dataset size as validated on the IEEE 39-bus system.
Traditional methods for solvability region analysis can only have inner approximations with inconclusive conservatism. Machine learning methods have been proposed to approach the real region. In this letter, we propose a deep active learning framework for power system solvability prediction. Compared with the passive learning methods where the training is performed after all instances are labeled, the active learning selects most informative instances to be label and therefore significantly reduce the size of labeled dataset for training. In the active learning framework, the acquisition functions, which correspond to different sampling strategies, are defined in terms of the on-the-fly posterior probability from the classifier. The IEEE 39-bus system is employed to validate the proposed framework, where a two-dimensional case is illustrated to visualize the effectiveness of the sampling method followed by the full-dimensional numerical experiments.