Forecasting requirements for Smart4RES developments are described in 11 Use Cases and 8 specific KPIs, presented in Deliverable D1.1. New forecasting products covering expected developments in power systems have been identified in Deliverable D1.2.
Improved Numerical Weather Predictions (NWP) have been generated at high resolution and the physical modelling of solar irradiance has been improved. The wealth of information contained in ensembles is transformed into useful forecasting products for RES applications. Local predictions at sub-minute temporal resolution are produced via the integration of a network of all-sky-imagers, the combination of multiple data sources and the simulation of turbulent weather processes through Large Eddy Simulation (LES). These forecasting products are presented in Deliverables D2.1 D2.2 D2.3 and D2.4. The RMSE of wind speed and solar irradiance forecasts is improved in the order of 10%.
Multi-source data approaches have been proposed to improve short-term RES forecasting. Modern statistical and machine learning models efficiently exploit the information contained in new data sources including high-resolution weather data produced by Smart4RES, presented in Deliverables D3.1 D3.2 and D3.3. Forecasting models reach or exceed the project KPI target values of 9-12% (solar) and 7-9% (wind) RMSE improvement for the up to 30-min ahead forecast.
Privacy-preserving collaborative forecasting and distributed learning approaches presented in Deliverable D4.1 set a new standard within the field of renewable energy forecasting, enabling to share distributed data and improve forecasting performance. This is transformed into new revenue streams for RES-related data providers thanks to the cutting-edge proposal of a data market for energy applications developed in Deliverable D4.2. Business models associated to collaborative analytics and data markets for renewable energy have been presented in Deliverable D4.3.
Dynamic security-constrained unit commitment/economic dispatch proposed in D5.2 enable to decrease load shedding events by more than 85%, hereby exceeding the KPI target value of 80%. The predictive management tool for distribution grid in D5.3 allows the operator to decide when to book flexibility to minimize flexibility activation cost, which leads to a reduction of 30% in a cost-loss matrix performance metric compared to a flexibility taken now without waiting for later RES forecast updates.
Prescriptive analytics combine forecasting and optimization to deploy explainable trading decisions, via a single model instead of four models for the case of RES trading on the day-ahead market. Distributionally robust optimization hedges trading strategies against high uncertainties in RES production and market prices. Both approaches are presented in Deliverable D5.4.
Living labs presented in D6.2 have demonstrated the operational feasibility of a forecasting and dynamic security assessment of islands with high RES penetration.
The costs and benefits of selected forecasting and decision-aid tools have been compared in Deliverable D6.4.
Lastly, 16 recommendations have been produced on open data, market rules, RES forecasting requirements and evolutions in grid codes.
Among results generated by the action, the consortium has identified 20 innovative key exploitable results, 14 of which have been identified with commercial potential in a 2-5 years horizon.
Regarding dissemination, the project led to 44 publications in journals and peer-reviewed conferences, 70 presentations in conferences, organized 5 webinars and 1 final conference in-person in Paris.
