Sparse Linear Models Applied to Power Quality Disturbance Classification

The automatic recognition of Power Quality (PQ) disturbances can be seen as a pattern recognition problem, in which different types of waveform distortion are differentiated based on their features. Similar to other quasi-stationary signals, PQ disturbances can be decomposed into time-frequency dependent components by using time-frequency or time-scale dictionaries. Short-time Fourier, Wavelets, and Stockwell transforms are some of the most common dictionaries used in the PQ community. Previous works about PQ disturbance classification have been restricted to the use of one of the above dictionaries. Taking advantage of the theory behind sparse linear models (SLMs), we introduce a sparse method for PQ representation, starting from overcomplete dictionaries. We apply Group Lasso. We employ different types of time-frequency dictionaries to characterize PQ disturbances and evaluate their performance under different pattern recognition algorithms. We show that SLMs promote the sparse basis selection improving the classification accuracy.