• it/

Search in the site by keyword

Publications - Paper

Automated Tool Based on Deep Learning to Assess Voltage Dip Validity: Integration in the QuEEN MV network Monitoring System

Related tags

#Electricity Network #Quality of Supply

Publications - Paper

Automated Tool Based on Deep Learning to Assess Voltage Dip Validity: Integration in the QuEEN MV network Monitoring System

This article presents QuEEN PyService, a software tool that has led to the automation of the extraction of voltage waveforms associated with voltage dips from the QuEEN distribution network monitoring system database, for advanced Power Quality analysis.

The application enabled the integration of the classifier, recently developed by RSE, DELFI (DEep Learning for False voltage dips Identification), making its intensive validation on a large number of voltage dips possible for the first time. Thanks to this tool, a comparison was made between the performances of the DELFI criterion and those of the previous criterion used in the QuEEN system based on the measurement of the 2nd harmonic using the data recorded by 61 measuring instruments in the period 2015-2020.
The analysis focused on the evaluation of traditional indicators used such as the N2a and N3b indices. The results show that using the DELFI classifier increases N2a and N3b by 20.6% and 38.8%, respectively, compared to the criterion currently used in QuEEN.

Rif.RSE​

21001887

Destination​

19th International Conference on Renewable Energies and Power Quality (ICREPQ’21), Almeria (Spain), July 28-30, 2021

Publication Date

30 July 2021

Authors​

M. Zanoni, R. Chiumeo, L. Tenti, M. Volta (RSE S.p.A.)

Publication Type

Paper

Projects

Architecture and management models of the electrical system and grids (EvolveNet)

Related tags

#Electricity Network #Quality of Supply

Comments