Bootstrap aggregation with Christiano–Fitzgerald random walk filter for fault prediction in power systems

The ability to predict and preempt insulator failures holds the potential to enhance the reliability of electrical power grids. The increase in insulator leakage current is an indication that failures may occur. By harnessing historical data and employing time series forecasting models, it is possible to identify potential faults before they escalate into disruptive failures. In this paper, a hybrid model for time series prediction is proposed by combining the Christiano–Fitzgerald random walk filter for signal denoising with an ensemble bootstrap aggregation model for leakage current forecasting. A comparison between bootstrap aggregation, boosting, random subspace, and stacked generalization ensemble learning models is presented. With a root mean square error of 7.62  \(\times 10^{-4}\) $\times {10}^{-4}$ (in a statistical evaluation), the ensemble bootstrap aggregation model with Christiano–Fitzgerald random walk filter proved to be a promising approach to be applied for time series fault forecasting. The proposed method was shown to be more promising than the original ensemble bootstrap aggregation model and the long short-term memory.