AI.grids aims to build the first Pan-European AI foundation model for power grid operations through a collaborative ecosystem of system operators, research organisations, and technology providers. Inspired by advances in large-scale AI models in other domains, the initiative aims to develop a shared model capable of learning from diverse grid datasets and supporting multiple operational applications, ranging from forecasting and congestion management to planning and asset monitoring.
DyPSOS (Dynamic Power System model Optimisation and Surrogates) develops an open-source automated framework that bridges the gap between generic and black-box models, without requiring access to proprietary model internals.
JoDyMoTePS (Joint Dynamic Modelling & Testing of Power Systems) is an open-source framework enabling TSOs, DSOs, equipment manufacturers and renewable energy developers to share privacy-preserving models of sub-parts of the European interconnected grid and to perform realistic dynamic co-simulations — without any party exposing sensitive data.
COLib-EB (COLib — Equation-Based) extends CRESYM's COLib library with a complete equation-based representation layer for all ~400 models defined in IEC 61970-457, making COLib the reference implementation that unites model data, mathematical equations and executable behaviour under one open-source framework.
COLib-SOGL provides TSOs with the technical architecture, processes and simulation methodology needed to comply with their SO GL obligations for dynamic data exchange and stability assessment — covering conventional equipment, HVDC systems, SGUs and FACTS devices.
CSL-TD (Causal Survival Learning with Time-Dependent covariates) develops a rigorous methodological framework for causal survival analysis applied to industrial assets, enabling operators to quantify the true effect of controllable variables — maintenance strategies, operational decisions — on asset time-to-failure, using observational data alone.
uSCC aims at inventing a new quasi-static short-circuit current simulator, embedding adequate modelling of IBRs, FACTS, HVDC and load. This new approach (simulator, assumptions and validation) could replace the existing one for equipment dimensioning during the planning phase and push the update of the current standard.
Power system networks are undergoing a rapid transformation due to the increasing integration of renewable energy sources (RES), decentralization of electricity generation, and the gradual retirement of conventional synchronous generators. The overarching objective of U-man is to investigate the different schemes that can be developed to enable TSO-DSO coordination.
PSSIx will propose and develop new stability indexes for power systems with increased penetration of inverter-based resources. Depending on the type of stability, the index can determine the stability of the grid or designate the area or the devices that are weakening the grid.
DC‑BL explores PowSyBl as a common, open-source and extensible simulation framework for AC-DC models with multi-terminals DC subnetworks. PowSyBl (Power System Blocks) natively supports CIM/CGMES formats, enabling consistent and interoperable data exchange between TSOs across Europe.
