Periodic Reporting for period 3 - Smart4RES (Next Generation Modelling and Forecasting of Variable Renewable Generation for Large-scale Integration in Energy Systems and Markets)
Période du rapport: 2022-05-01 au 2023-04-30
Forecasting renewable energy production is a mature discipline, but forecasting errors are still significant, in particular in challenging weather conditions. These errors impact the competitiveness of RES in electricity markets and impede a large penetration of RES into power systems.
This is why the overarching objective of Smart4RES is to develop and test tools that enable an increase of at least 15 % in RES forecasting performance, and enhance value in applications by considering the entire modelling and value chain of RES forecasting.
A first objective of the project consists in defining requirements for forecasting technologies to enable near 100% RES penetration by 2030 and beyond. Based on these requirements, Smart4RES proposes RES-dedicated weather forecasting and new RES production forecasting tools, using various sources of data and developing high-resolution approaches.
An optimal extraction of value from RES data and forecasts is crucial to further develop RES forecasting and associated services. Smart4RES proposes new forecasting products, data markets and new business models in order to remunerate agents who contribute to an increase in RES forecasting quality and value in applications.
Finally, Smart4RES addresses the value of RES forecasting in power system applications such as trading in electricity markets and provision of system services to TSOs and DSOs. Data-driven solutions aim at simplifying the model chain from data to decision. Decision-aid tools are designed to enable a large penetration of RES production, combined with storage.
Living labs based on digital twins of Greek islands demonstrate the operational performance of data-driven security assessment able to reduce load shedding.
Cost-benefit analysis assess the value of forecasting and decision-aid tools for trading and grid management.
This is why the overarching objective of Smart4RES is to develop and test tools that enable an increase of at least 15 % in RES forecasting performance, and enhance value in applications by considering the entire modelling and value chain of RES forecasting.
A first objective of the project consists in defining requirements for forecasting technologies to enable near 100% RES penetration by 2030 and beyond. Based on these requirements, Smart4RES proposes RES-dedicated weather forecasting and new RES production forecasting tools, using various sources of data and developing high-resolution approaches.
An optimal extraction of value from RES data and forecasts is crucial to further develop RES forecasting and associated services. Smart4RES proposes new forecasting products, data markets and new business models in order to remunerate agents who contribute to an increase in RES forecasting quality and value in applications.
Finally, Smart4RES addresses the value of RES forecasting in power system applications such as trading in electricity markets and provision of system services to TSOs and DSOs. Data-driven solutions aim at simplifying the model chain from data to decision. Decision-aid tools are designed to enable a large penetration of RES production, combined with storage.
Living labs based on digital twins of Greek islands demonstrate the operational performance of data-driven security assessment able to reduce load shedding.
Cost-benefit analysis assess the value of forecasting and decision-aid tools for trading and grid management.
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.
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.
Weather forecasting innovations:
- Pseudo-deterministic forecasts were constructed to exploit the high-resolution ensemble weather predictions and better predict infra-hour variability of wind speed in a user-friendly way for RES applications.
- LES provide realistic high-resolution weather variability on case studies with complex terrain.
- High-resolution regional forecasts of solar irradiance were derived from an array of all-sky imagers covering a large region in northern Germany.
RES power forecasting innovations:
- PV forecasting model harvesting lightning data, high-resolution irradiance maps
- Seamless RES power forecasting over multiple timeframes
- Wind turbine forecasting model for seconds-ahead using machine learning and LIDAR data
Innovations in optimal extraction of value from data:
- Cutting-edge method for privacy-preserving collaborative RES forecasting
- Algorithmic solutions for a data marketplace of RES applications
- the PREDICO platform will play a major role in unleashing the value of distributed energy data
Innovations in decision-aid tools for RES trading and grid management:
- Machine-learning based approach for dynamic security assessment in isolated power systems reduces the modelling effort
- Data-driven predictive management of distribution grids allows the operator to take risk-informed decision regarding flexibility activations and potentially avoid grid reinforcement
- Prescriptive analytics simplify the decision-making model chain and explain the impact of input data on decision cost
Socio-economic impacts:
- Increased trading revenues, reduced investments and total costs may be transferred to a higher scale, e.g. regional or national. This is also true for carbon emissions associated to fossil dispatchable plants in interconnected and isolated power systems.
- Smart4RES has increased awareness about RES forecasting and application with its series of 5 webinars and 45+ publications.
- Pseudo-deterministic forecasts were constructed to exploit the high-resolution ensemble weather predictions and better predict infra-hour variability of wind speed in a user-friendly way for RES applications.
- LES provide realistic high-resolution weather variability on case studies with complex terrain.
- High-resolution regional forecasts of solar irradiance were derived from an array of all-sky imagers covering a large region in northern Germany.
RES power forecasting innovations:
- PV forecasting model harvesting lightning data, high-resolution irradiance maps
- Seamless RES power forecasting over multiple timeframes
- Wind turbine forecasting model for seconds-ahead using machine learning and LIDAR data
Innovations in optimal extraction of value from data:
- Cutting-edge method for privacy-preserving collaborative RES forecasting
- Algorithmic solutions for a data marketplace of RES applications
- the PREDICO platform will play a major role in unleashing the value of distributed energy data
Innovations in decision-aid tools for RES trading and grid management:
- Machine-learning based approach for dynamic security assessment in isolated power systems reduces the modelling effort
- Data-driven predictive management of distribution grids allows the operator to take risk-informed decision regarding flexibility activations and potentially avoid grid reinforcement
- Prescriptive analytics simplify the decision-making model chain and explain the impact of input data on decision cost
Socio-economic impacts:
- Increased trading revenues, reduced investments and total costs may be transferred to a higher scale, e.g. regional or national. This is also true for carbon emissions associated to fossil dispatchable plants in interconnected and isolated power systems.
- Smart4RES has increased awareness about RES forecasting and application with its series of 5 webinars and 45+ publications.