Wind Energy Forecasting Based on Various Weather Parameters

Thumbnail Image
Che Siti Amira binti Md Azmi
Journal Title
Journal ISSN
Volume Title
Research Projects
Organizational Units
Journal Issue
Wind energy resource is a never-ending resource that categorized under renewable energy or sustainable manners. Electricity generated from wind When the wind blows across the wind turbine system, it produces high kinetic energy once it goes through the wind blades, it will rotate and turn it into useful mechanical energy. That motion of the generator produces electricity. However, in Malaysia, the inconsistency in terms of wind speed required for wind turbines to operate to generate electricity is a major problem. Different locations have different weather parameters that affect wind speed and wind energy production. In this paper, the wind energy forecasting is performed using linear, nonlinear, and deep learning models for small scale wind turbine. The paper focus on comparing and correlating performance of univariate and multivariate input parameters with wind speed as its primary feature using short term forecasting with time horizon of 1 hour ahead. The set location is at Mersing, Johor where it is prominently one of the locations in Malaysia with constant, high amount of wind speed. It is found that Huber Regressor, Gradient Boosting, and CNN are shown to be powerful in prediction. Huber Regressor has the best MAE of 0.597 and RMSE of 0.797 while Gradient Boosting has the best R² at 0.637. CNN has the best MAPE at 30.861 and shown to be the most optimum forecasting model for univariate parameter. The results show that the outcome of the evaluation does not vary significantly depending on the criteria chosen in the data selection.
Interim Semester 2020/2021
Wind Energy Forecasting