A heterogeneous distributed prediction model for wind-solar energy production
To achieve the European Union's green transition goal, solar photovoltaic (PV) and wind energy are widely adopted, which pose great challenges to the reliability and safety of existing energy systems. The state-of-the-art methods...
ver más
¿Tienes un proyecto y buscas un partner? Gracias a nuestro motor inteligente podemos recomendarte los mejores socios y ponerte en contacto con ellos. Te lo explicamos en este video
Proyectos interesantes
RTC-2017-6635-3
DESARROLLO DE UN MOTOR INTELIGENTE DE PREDICTORES EÓLICOS
327K€
Cerrado
TIN2014-54583-C2-2-R
NUEVOS ALGORITMOS HIBRIDOS BIO-INSPIRADOS PARA PROBLEMAS DE...
65K€
Cerrado
ENE2009-14582-C02-02
NUEVAS METODOLOGIAS DE EVALUACION Y PREVISION DE RECURSOS RE...
36K€
Cerrado
PCI2018-093043
INTRA-HOUR PREDICTION OF SOLAR ELECTRICITY GENERATION FROM P...
111K€
Cerrado
PVOP
Digitalising the PV sector for the era of Terawatts
6M€
Cerrado
TIN2014-54583-C2-1-R
ALGORITMOS DE CLASIFICACION ORDINAL Y PREDICCION EN ENERGIAS...
96K€
Cerrado
Información proyecto ANSWER
Duración del proyecto: 30 meses
Fecha Inicio: 2023-07-13
Fecha Fin: 2026-01-31
Descripción del proyecto
To achieve the European Union's green transition goal, solar photovoltaic (PV) and wind energy are widely adopted, which pose great challenges to the reliability and safety of existing energy systems. The state-of-the-art methods mainly concentrate on the prediction of a single energy form, either wind or solar. There is limited research on joint forecasting for wind-solar energy due to the challenges of data heterogeneity and data silos for different wind farms and solar PV plants. This project develops a heterogeneous distributed prediction model for joint wind-solar energy production (ANSWER), based on heterogeneous data sources at different wind farms and solar PV plants. A global model will be generated by the fusion of heterogeneous models from all wind farms and solar PV plants, coordinated by a central server. To achieve the research goal, this project proposes four work packages, including 1) development of model specifications, which use a two-level structure:client-level and server-level, 2) development of a generic seamless forecasting client model that supports multiple time-scale and -horizon prediction, 3) model aggregatioin for heterogeneous client models, and 4) model deployment and evaluation in a living lab for the robustness of the proposed ANSWER model. This proposal ANSWER specifies the resources needed for this project, including the quality and capacity of the host university, mentors, data, and experimental facilities. This project will enhance the scientific skills and innovation capability, expand research horizons, and establish research collaborations of the applicant. A two-way knowledge transfer approach in energy big data, distributed modeling and energy system analysis is proposed to ensure benefits between the applicant and the host university. The proposed model will make a significant contribution to the state of the art in renewable energy (wind and solar) production forecasting and the EU climate goals.