FExWaveS application for voltage dips origin assessment: optimization of the tool in views of its integration into the QuEEN monitoring system

Abstract

This paper presents the integration of the FExWaveS (Features Extraction from Waveform Segmentation) application in the QuEEN distribution network monitoring system. The application attributes a shape factor to each voltage dip to make it easier to classify voltage dips origin, namely, to assess the events source location (upstream or downstream from the point of measurement). The classification is carried out by a Machine Learning algorithm. The integration in the QuEEN system has been achieved thanks to QuEEN PyService, an automated tool developed by RSE aimed to the extraction of events voltage signals from QuEEN database. This application has allowed the integration of the FExWaveS classifier in a real scenario making it possible the intensive validation of the latter on a large number of voltage dips for the first time.