Dataset for Training and Testing Data-driven Security Assessment of the IEEE ELVTN

This repository contains the datasets produced using different data generation strategies to train data driven models (e.g., decision trees, gradient tree boosting, and deep neural networks), and to evaluate their performances. The data generation strategies are described, and the results are presented in the conference paper: "Training Data Generation Strategies for Data-driven Security Assessment of Low Voltage Smart Grids" J. Cuenca, E. Aldea, E. Le Guern-Dall'o, R. Féraud, G. Camilleri, and A. Blavette. IEEE ISGT EU 2024, Dubrovnik, Croatia, Oct 2024. Each operational point (rows in "input_injections_kW.csv") is the active power injection associated to each node of the IEEE European Low Voltage Test Network, and the security assessment performed using a balanced version of the network in OpenDSS (binary values in "output_classification_notsafe.csv" where 1 is label "not safe", and 0 is "safe"). Each subfolder includes one million operational points generated using a different strategy as described in the paper. These datasets are provided for replicability.