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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In the power system, security assessment (SA) plays a pivotal role indetermining the safe operation in a normal situation and some contingenciesscenarios. Electrical variables as input variables of the model are mainlyconsidered to indicate the power system operation as secure or insecure,according to the reliability criteria for contingency scenarios. In thisapproach, the features are in grid format data, where the relation betweenfeatures and any knowledge of network topology is absent. Moreover, thetraditional and common models, such as neural networks (NN), are not applicableif the input variables are in the graph format structure. Therefore, this paperexamines the security analysis in the graph neural network (GNN) framework suchthat the GNN model incorporates the network connection and node's neighbors'influence for the assessment. Here the input features are separated graphsrepresenting different network conditions in electrical and structuralstatuses. Topological characteristics defined by network centrality measuresare added in the feature vector representing the structural properties of thenetwork. The proposed model is simulated in the IEEE 118-Bus system for thevoltage static security assessment (SSA). The performance indices validate theefficiency of the GNN-based model compared to the traditional NN model denotingthat the information enclosed in graph data boosts the classifier performancesince the GNN model benefits the neighbors' features. Moreover, outperformingof GNN-based model is determined when robustness and sensitivity analyzes arecarried out. The proposed method is not limited to a specific task and can beextended for other security assessments with different critical variables, suchas dynamic analysis and frequency criteria, respectively.

Graph Neural Network Framework for Security Assessment Informed by Topological Measures