| dc.description.abstract | This paper presents an end-end study focused on improving grid reliability with the
application of Graph Neural Networks (GNNs). Graph representation of the electrical
grid yields the model of nodes of substations and transformers interconnection of
power lines constructed by the data from the National Grid Electricity System Operator
(ESO) Data Portal. Based on their connections, node feature updating and encoding
by predicting grid reliability with a multi-layered Graph Attention Network (GAT) was
employed. In predicting failure regions, the proposed model with rigorously trained
and tested state shows higher accuracy compared to existing methods. The results of
the model signify the model’s capability to efficiently manage large-scale data with
actionable insight generation for specific use in cases such as predictive maintenance,
which ensures the resilience of modern power systems and integrating renewable energy
in the modern power system. | en_US |
