Wind forecast at medium voltage distribution networks

11/25/2022

Due to the intermittent and variable nature of wind, Wind Power Generation Forecast (WPGF) has become an essential task for power system operators, who are looking for a reliable wind penetration into the electric grid. Since there is a need to forecast wind power generation accurately, the main contribution of this thesis is the development, implementation and comparison of WPGF methods to be used by Distribution System Operators (DSOs). The methodology applied comprised five stages namely, pre-processing, feature selection, forecasting models, post-processing and validation. For training and testing the models, historical wind power generation data (measured at secondary substations) of 20 wind farms connected to the Medium Voltage (MV) distribution network was provided by the Portuguese DSO, while meteorological data was obtained from IPMA and ISTMeteo. After comparing the accuracy of eight different models in terms of their Relative Root Mean Square Error (RRMSE), Extreme Gradient Boosting (XGBOOST) appeared as the best-suited forecasting method for wind power generation. Thus, XGBOOST was chosen for further tests and improvements (tuning) in order to reduce the error as much as possible. At the end, the best average RRMSE achieved by the proposed XGBOOST model for 1 year training (JAN-DEC of 2020) and 6 months forecast (JAN-JUN of 2021) corresponds to 13.48%, outperforming the predictions of the Portuguese DSO by more than 20%, which for the same period of analysis present a RRMSE of 16.88%.

Authors in the community:

• 

  H

  Herbert Amezquita Ortiz

  ist1100758

Supervisors of this institution:

• 

  P

  Pedro Manuel Santos de Carvalho

  ist13407

• 

  H

  Hugo Gabriel Valente Morais

  ist428549

mechanical-engineering - Mechanical engineering

eng - English

Instituto Superior Técnico