Frequency-based Multi Task learning With Attention Mechanism for Fault Detection In Power Systems
This addresses the critical need for accurate fault detection in smart grids, offering an incremental improvement over existing data-driven methods by enhancing interpretability and performance.
The paper tackles fault detection in power systems by introducing a deep learning approach that combines LSTM with attention and 1D-CNN for frequency analysis, along with unsupervised clustering and multi-task learning, achieving performance that surpasses Kaggle competition winners and state-of-the-art methods in metrics like accuracy.
The prompt and accurate detection of faults and abnormalities in electric transmission lines is a critical challenge in smart grid systems. Existing methods mostly rely on model-based approaches, which may not capture all the aspects of these complex temporal series. Recently, the availability of data sets collected using advanced metering devices, such as Micro-Phasor Measurement units ($μ$ PMU), which provide measurements at microsecond timescale, boosted the development of data-driven methodologies. In this paper, we introduce a novel deep learning-based approach for fault detection and test it on a real data set, namely, the Kaggle platform for a partial discharge detection task. Our solution adopts a Long-Short Term Memory architecture with attention mechanism to extract time series features, and uses a 1D-Convolutional Neural Network structure to exploit frequency information of the signal for prediction. Additionally, we propose an unsupervised method to cluster signals based on their frequency components, and apply multi task learning on different clusters. The method we propose outperforms the winner solutions in the Kaggle competition and other state of the art methods in many performance metrics, and improves the interpretability of analysis.