Forecasting and Analysis of Transient Voltage with Random Forest Regressor

This research addresses the critical challenge of predicting transient voltage events in electrical appliances. Transient voltages are temporary deviations from normal voltage levels that can damage electrical appliances and cause power interruptions if not addressed preemptively. Currently, limitations exist in detecting and forecasting these events across various electrical systems. This study investigates the value of predictive strategies to minimize transient voltage risks. Utilizing simulated data from RLC circuits, we train multiple machine learning regressor models to estimate transient onset times and predict voltage at specific timestamps using time series analysis and lag-based forecasting. Our approach demonstrates promising accuracy and lower error rate as measured by key performance metrics, opening doors for preventive measure of appliances. These findings provide essential insights into data-driven forecasting of transient voltages, paving the way for the development of a more resilient and reliable electrical infrastru cture.