Belangrijkste concepten
This paper introduces an algorithm for generating large, realistic synthetic datasets of power injections in electric power grids, addressing the challenge of limited access to real-world operational data for training machine learning models in the power systems domain.
Statistieken
The PanTaGruEl model of the synchronous grid of continental Europe, used in this study, consists of 7822 power lines and 553 transformers connecting 4097 buses, with 1083 generators.
The study utilizes 9 years of ENTSO-E data (2015-2023) for national load distributions.
The Pearson correlation coefficient between pairs of synthetic time series is set to 0.8, based on real-world data from the Swiss transmission grid.
The study uses a maximum ramping rate of 200 MW per hour for coal-fired power plants.
The dataset repository contains 20 tables of each data type (loads, generators, lines), representing 20 years of synthetic data.