A novel technique for forecasting the optimal production of a wind generator installed at any geographical point located within a very large area

• Published in: Journal of Electrical Systems and Information Technology Vol. 10; no. 1; pp. 23 - 33
• Main Authors: Agbomahena, Bienvenu Macaire, Didavi, Kossoko Babatoundé Audace, Agbokpanzo, Richard Gilles
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.12.2023; Springer Nature B.V; SpringerOpen
• Subjects: Alternative energy sources; Artificial Intelligence; Climate change; Clustering; Electrical Engineering; Electrical Machines and Networks; Energy resources; Engineering; Environmental policy; Environmental protection; Forecasting; Fossil fuels; Generators; Information Systems and Communication Service; K-means model; LSTM; Mathematical models; Mechanical Engineering; Meteorological parameters; Optimal production; Optimization; Power Electronics; Renewable energy sources; Renewable resources; Time series; Turbines; Weather forecasting; Wind direction; Wind power; Wind speed; Wind turbines; Windpowered generators; Optimal production; means model; LSTM; Wind speed; Wind power; Forecasting
• ISSN: 2314-7172; 2314-7172
• DOI: 10.1186/s43067-023-00091-4

The need to integrate renewable energy sources into the energy mix is felt because of the many advantages they offer over fossil fuels, notably in terms of environmental protection and more uniformly distributed availability. The intermittent and stochastic ones, such as wind power, present many problems to network operators due to the volatile nature of their output power. This work presents a new technique for optimally forecasting the power output of a wind turbine installed at any geographic point located within a very large area. Once the study area is defined, it is gridded and optimally sampled in order to have a truly representative number of geographical points. The study area is then divided into sub-areas by grouping the samples by similarity of variation of meteorological parameters (wind speed and direction). For each sub-area, the optimal production periods are then identified and used for forecasting the power output. The forecasting technique used combines the LSTM model for forecasting meteorological parameters and the linear model for approximating the power curves of wind turbines. The technique was applied to the Beninese territory on which 90 sub-zones were formed. A 12 h forecasting of wind speed, wind direction and wind power were presented for one of the sub-areas. The clustering results gave a Silhouette score of at least 0.99. The wind speed and direction forecasting gave (0.34 m/s, 7.8 rad) and (93%, 70%) for RMSE and R 2 , respectively.