GridData
Description: GridData is a European metrology project aimed at making data-driven analysis of power grids more trustworthy. It develops ways to assess the reliability of voltage and current measurements from existing grid sensor networks, including machine-learning methods for flagging faulty readings, and builds reference datasets and digital-twin models of real grids to test these methods under realistic conditions. Building on this foundation, the project develops and benchmarks AI-based techniques for detecting abnormal grid events, such as frequency deviations, sub-synchronous oscillations, power quality disturbances and equipment faults, together with quantified uncertainty, and produces forecasting methods and good-practice guidance to help metrology institutes, standards bodies and grid operators adopt these approaches.
Duration: 06/2025–05/2028