Various pattern recognition methods have been suggested for estimating high-voltage alternating current transmission line fault location. However, insufficient studies have been conducted on the transmission lines connected to hybrid power generation systems such as wind and solar plants. In this study, the performance of different regression methods was investigated on a hybrid power system. Different faults with random distances on the transmission line were simulated and a fault database created by recording the current and voltage signals of these faults. After normalising this data in the pre-processing phase, it was passed to the digital signal processing stage. By repeating the experiments, 497 different faults were created. Fault types, fault resistances, and fault inception angles were changed randomly in order to obtain similar fault occurrence conditions as in real life by writing a Matlab code. In order to obtain distinctive features, the discrete wavelet transform was used. For training and validation of the dataset, Matlab Regression Learner App (RLA) was employed and the obtained results compared to select the best model. After significant fault simulation, Matern 5/2, a type of Gaussian progress regression model, showed more promising results compared to other RLA models.