We will develop a data-driven cable replacement method to address the utility’s concern on accelerated cable failure due to fast-growing EVs

A novel spatio-temporal GCN-based generic hierarchical fault location method for both traditional AC systems and future AC-HVDC systems.

We will develop an ensemble learning approach to stabilize the prediction accuracy and thus increase the algorithm robustness.

A novel data labeling scheme and a novel spatio-temporal graph neural network model will be developed to automate the oscillation analysis.