Data-driven time series reconstruction for modern power systems research

A critical aspect of power systems research is the availability suitable data, access to which limited by privacy concerns and sensitive nature energy infrastructure. This lack in turn, hinders development modern avenues such as machine learning approaches or stochastic formulations. To overcome this challenge, paper proposes a systematic, data-driven framework for reconstructing high-fidelity time series, using publicly-available grid snapshots historical data published transmission system operators. The proposed approach, from geo-spatial generation capacity reconstruction, series disaggregation, applied French grid. Thereby, synthetic but highly realistic spanning multiple years with 5-minute granularity, generated at individual component level.