An Edge-Deployable Lightweight Dynamic Spatio-Temporal Graph Neural Network for Joint Distribution-Network Line-Loss Prediction and Operating-State Recognition
A lightweight dynamic spatio-temporal graph neural network, EdgeLite-DSTGNN, is proposed to address the intensified spatio-temporal coupling of line-loss rates, complex state correlations, and limited edge-terminal resources in distribution networks with high renewable-energy penetration. The method treats branches as...