Detecting Faults in VSC-HVDC Systems by Deep Learning and K-means

Background: The present paper compared two methods that are employed to determine the fault location in VSC-HVDC transmission lines. These systems are widely recognized for their fast and reliable control. Methods: Wavelet transform was employed as an advanced technique of signal processing to extract important characteristics of fault signal from both sides of the line by phasor measurement unit (PMU). Deep Learning was implemented to identify the relationship between the extracted features from the wavelet analysis of fault current and variations under fault conditions. Wavelet transform and advanced signal processing techniques were adopted to extract important features of fault signals from both sides of the line by PMU. Results: The results indicated the high accuracy of finding fault location by the deep learning algorithm method compared to the k-means algorithm with an error rate of <1%. Conclusion: Studies on the 50 kV VSC-HVDC transmission line with a length of 25 km in MATLAB have been conducted.