A new approach for event detection in smart distribution oscillograph recorders

This paper presents some new results for a fundamental step in automatic oscillography analysis: transient detection. We performed experiments with usual detection methods, such as the Kalman filter (KF) and autoregressive (AR) models, and we are proposing a new method based on the Discrete Wavelet Transform (DWT) and Support Vector Data Description (SVDD). Data simulated in the Alternative Transient Program (ATP) was generated for comparison and validation of detection performance. The results presented here demonstrate that the proposed detection method based on DWT and SVDD yields better overall performance for the transient detection process when compared to currently used methods such as KF and AR models. These results show the potential for possible embedded applications in automatic oscillographic recorders in smart distribution networks, in which identification, characterization, and mitigation of events is critical for network operation and maintenance.