ABSTRACT
Quality of power has become an issue of main concern to the service providers as well consumers of electricity. Power quality (PQ) disturbances are caused due to the use of the devices based on solid state switching components. PQ disturbances lead to failure of equipment, mis-operation of protection equipment, inaccurate metering, and reduction in efficiency of appliances. This is intensified when two or more PQ disturbances are incidents simultaneously. Detection and classification of complex PQ issues will help to find the cause of these disturbances. An approach for identification of complex PQ disturbances is proposed in this work. This technique is based on processing of the signals using the Stockwell transform to compute output matrix in frequency domain. A power quality index (PQI) and a PQ time location index (PQTLI) are proposed, which are computed from this matrix and used for identification of the different types of complex PQ issues. Six statistical features are computed from the PQI and PQTLI that are considered as input data for the decision tree for classifying the PQ events. The Stockwell transform and rule-based decision support technique is effective in identification of complex PQ issues. The classification accuracy of the complex PQ issues has been achieved as high as 96.2%. A performance comparison of the technique is undertaken to compare with accuracy the algorithm based on the discrete wavelet transform (DWT) and artificial neural network (ANN) and found superior compared to the DWT and ANN-based approach.
