Power Quality Event Classification in Distribution Grids Using Machine Learning

With the penetration of non-linear loads, renewables and distributed generation with power electronic converters, solutions for maintaining good power quality have become a major concern for the stakeholders of electrical power systems. In this paper, a machine learning based model for power quality event classification is developed and tested. 16 categories of the most commonly occurring power quality events are classified by means of wavelet transform and select machine learning based methods to evaluate the best performing machine learning model. The outcome of classifications and effectiveness of machine learning methods is evaluated using the ‘Classification Learners’ application in MATLAB. The selected machine learning model is implemented in Simulink for test distribution grid circuits. The results obtained from simulation showed acceptable accuracy and performance and demonstrated the efficiency of the model in different operating conditions.