Wind Power Forecasting with Machine Learning: Single and combined methods

Authors

  • J. Rosa Author
  • R. Pestana Author
  • C. Leandro Author
  • C. Geraldes Author
  • J. Esteves Author
  • D. Carvalho Author

DOI:

https://doi.org/10.24084/repqj20.397

Keywords:

Wind power forecast, feature engineering, machine learning, ensemble models, recurrent neural network

Abstract

In Portugal, wind power represents one of the largest renewable sources of energy in the national energy mix. The investment in wind power started several decades ago and is still on the roadmap of political and industrial players. One example is that by 2030 it is estimated that wind power is going to represent up to 35% of renewable energy production in Portugal. With the growth of the installed wind capacity, the development of methods to forecast the amount of energy generated becomes increasingly necessary. Historically, Numerical Weather Prediction (NWP) models were used. However, forecasting accuracy depends on many variables such as on-site conditions, surrounding terrain relief, local meteorology, etc. Thus, it becomes a challenge to obtain improved results using such methods. This article aims to report the development of a machine learning pipeline with the objective of improving the forecasting capability of the NWP’s to obtain an error lower than 10%.

Author Biographies

  • J. Rosa

    epartment of Mathematics, Electrical Engineering 
    Instituto Superior de Engenharia de Lisboa – Lisbon, Portugal 

  • R. Pestana

    Department of Mathematics, Electrical Engineering 
    Instituto Superior de Engenharia de Lisboa – Lisbon, Portugal 

    System Operator Division 
    REN - Rede Eléctrica Nacional, S.A. – Lisbon, Portugal

    R&D NESTER 
    Centro de Investigação em Energia REN - State Grid, S.A. – Lisbon, Portugal 

  • C. Leandro

    Department of Mathematics, Electrical Engineering 
    Instituto Superior de Engenharia de Lisboa – Lisbon, Portugal 

  • C. Geraldes

    Department of Mathematics, Electrical Engineering 
    Instituto Superior de Engenharia de Lisboa – Lisbon, Portugal

    CEAUL, Centro de Estatística e Aplicações, Universidade de Lisboa – Lisbon, Portugal 

  • J. Esteves

    R&D NESTER 
    Centro de Investigação em Energia REN - State Grid, S.A. – Lisbon, Portugal

  • D. Carvalho

    Department of Mathematics, Electrical Engineering 
    Instituto Superior de Engenharia de Lisboa – Lisbon, Portugal

Downloads

Published

2024-01-03

Issue

Section

Articles