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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The classification of anomalies or sudden changes in power networks versusnormal abrupt changes or switching actions is essential to take appropriatemaintenance actions that guarantee the quality of power delivery. This issuehas increased in importance and has become more complicated with theproliferation of volatile resources that introduce variability, uncertainty,and intermittency in circuit behavior that can be observed as variations involtage and current phasors. This makes diagnostics applications morechallenging. This paper proposes using quotient gradient system (QGS) to traintwo-stage partially recurrent neural network to improve anomaly classificationrate in power distribution networks using high-fidelity data from micro-phasormeasurement units (PMUs). QGS is a systematic approach to finding solutions ofconstraint satisfaction problems. We transform the PMUs data from the powernetwork into a constraint satisfaction problem and use QGS to train a neuralnetwork by solving the resulting optimization problem. Simulation results showthat the proposed supervised classification method can reliably distinguishbetween different anomalies in power distribution networks. Comparison withother neural network classifiers shows that QGS trained networks providesignificantly better classification. Sensitivity analysis is performedconcerning the number of PMUs, reporting rates, noise level and early versuslate data stream fusion frameworks.

Anomaly Classification in Distribution Networks Using a Quotient Gradient System