Advanced Machine Learning Functionalities in the Medium Voltage Distributed Monitoring System QuEEN: A Macro-Regional Voltage Dips Severity Analysis

This paper presents the integration of advanced machine learning techniques in the medium voltage distributed monitoring system QuEEN. This system is aimed to monitor voltage dips in the Italian distribution network mainly for survey and research purposes. For each recorded event it is able to automatically evaluate its residual voltage and duration from the corresponding voltage rms values and provide its “validity” (invalidating any false events caused by voltage transformers saturation) and its “origin”(upstream or downstream from the measurement point) by proper procedures and algorithms (current techniques). On the other hand, in the last years new solutions have been proposed by RSE to improve the assessment of the validity and origin of the event: the DELFI classifier (DEep Learning for False voltage dips Identification) and the FExWaveS + SVM classifier (Features Extraction from Waveform Segmentation + Support Vector Machine classifier). These advanced functionalities have been recently integrated in the monitoring system thanks to the automated software tool called QuEEN PyService. In this work, intensive use of these advanced techniques has been carried out for the first time on a significant number of monitored sites (150) starting from the data recorded from 2018 to 2021. Besides, the comparison between the results of the innovative technique (validity and origin of severe voltage dips) with respect to the current ones has been performed at the macro-regional level too. The new techniques are shown to have a not negligible impact on the severe voltage dips number and confirm a non-homogenous condition among the Italian macro-regional areas.

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

This paper presents the development of an automated tool called QuEEN PyService, aimed to the extraction of events voltage signals from the QuEEN distribution network monitoring system database, for advanced Power Quality analysis. The application has allowed the integration of the DELFI classifier (DEep Learning for False voltage dips Identification), recently developed by RSE, making it possible for the first time the intensive validation of the latter on a large number of voltage dips. Thanks to this tool, a comparison between the performance of DELFI and those of an older criterion based on the 2nd voltage harmonic measurement has been performed using data recorded by 61 measurement units in the period 2015-2020 The analysis has been focused on traditional PQ voltage dips counting indices as N2a e N3b. Results show that the usage of the DELFI classifier increases the N2a and the N3b by respectively the 20.6 % and 38.8% with respect to the QuEEN criterion.

Clustering Technique for Scenario Reduction in Post-Energy Transition Voltage Dips Assessment

The Dutch transmission system operator makes multiple scenarios to predict the future developments. These scenarios will help to define the risk factors and constraints in the grid, for which reinforcement planning is necessary. The developed grid after these reinforcements should continue to fulfil the power quality assessment criteria specified in the Dutch grid code. The reduction in system strength due to partial phase out of the conventional generation may have an adverse impact on the PQ, especially the voltage dips. Precise assessment criteria for voltage dips have been stipulated by the Dutch grid code that also need to be met after the energy transition. Evaluating all possible grid future scenarios can provide insight in possible future operating conditions. In practice, due to various combinations of network configurations, loading scenarios and dispatch scenarios, it is not possible to analyze all operating scenarios in detail. This paper presents a method to determine the most important scenarios for voltage dip assessments using a clustering technique. The proposed clustering technique reduces the number of scenarios that are needed to be assessed that makes the whole process doable in practice.

Modeling of Voltage Fluctuations Generated by Arc Furnaces

Arc furnaces can be classified as electricity receivers, which largely affect the quality of electricity in the power system. Voltage fluctuations are the main disturbance generated by arc furnaces. The effects of voltage fluctuations include the phenomenon of flickering light. Apart from voltage fluctuations, arc devices, to a lesser extent, are the source of current and voltage asymmetry, voltage curve distortion, and voltage dips. The main purpose of theoretical considerations is to assess the voltage fluctuations generated by arc furnaces. The article presents a model of an arc device in which the arc has been replaced by a voltage whose value depends on the arc length. It presents also the results of the analysis of measurements of the parameters characterizing voltage fluctuations and flicker indicators.