Data-Driven Time Series Reconstruction for Modern Power Systems Research

TL;DR

This paper introduces a data-driven framework to reconstruct high-fidelity, realistic time series data for power systems using publicly available data, addressing privacy concerns and enabling advanced research.

Contribution

It presents a novel systematic approach for generating detailed, multi-year, high-resolution time series data for power systems from publicly available information.

Findings

Successfully applied to the French transmission grid

Generates multi-year, 5-minute granularity data

Produces synthetic data with high realism

Abstract

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