English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

A fast charging station (FCS), which consists of eight fast and extreme chargers that operate individually and simultaneously, is considered in this research work. The FCS is supplied from the main grid as well as a Photovoltaic (PV) Farm that includes a two-unit array of 250 kW per array. The impact of the FCS on the voltage sag is quantified using two indices: a voltage sag energy index and a voltage sag severity index. The voltage sag severity is determined based on the sag duration, in accordance with the Semiconductor Equipment and Materials International Group (SEMI) curve. This paper subsequently aims to accurately determine the origin of voltage sag events, whether due to a fault (short circuit) in the system or due to a charging event that occurs at an FCS. The cases in which the voltage sag limit is violated are identified as normal events (due to charging events at the FCS) or anomaly events (due to faults), using a machine learning-based method. Both events of normal and anomaly are simulated based on a Monte Carlo method. Different wavelet functions of different orders are introduced to extract the events&#x2019; features relying on the change between cycles of the voltage and the current waveform. The minimum redundancy maximum relevance algorithm is applied to obtain an optimal set of features to improve the classification&#x2019;s performance. The results of voltage sag energy index indicate that the voltage sag energy is about 0.28 p.u. for almost 50% of the applied scenarios. Likewise, the sag severity index is more than one for nearly 50% of the charging events considered in this study. Moreover, the findings reveal that all normal and anomaly events are accurately classified using biorthogonal of order 3.9 when ensemble tree or na&#x00EF;ve Bayes classifiers are trained and tested by the proposed set of features. Not only can the overall performance of the power system be improved by accurately classifying normal and abnormal events, but power outages are also prevented and maintenance costs are reduced.

Voltage Sag Assessment, Detection, and Classification in Distribution Systems Embedded with Fast Charging Stations