Multi-step ahead ultra-short-term wind power forecasting

Multi-step ahead ultra-short-term wind power forecasting: A forecast quality and value comparison between proposed deep learning models and an operational numerical weather prediction based model

Homsma, Thom (TU Delft Electrical Engineering, Mathematics and Computer Science)

Watson, S.J. (mentor)
Basu, S. (graduation committee)
Visser, Vincent (graduation committee)
Quak, Truusje (graduation committee)

Delft University of Technology

Electrical Engineering | Sustainable Energy Technology

2021-08-18

The ongoing large scale adoption of wind power increases the associated risks related to the variability. An essential way to mitigate these risks for a utility company is to forecast production accurately. This study aims to create insight into the potential of deep learning models for both forecast quality and value on the ultra-short-term wind power forecasting (UST-WPF) horizon.

The status quo at Eneco, a Dutch utility company, for UST-WPF is a numerical weather prediction (NWP) based model with a rudimentary ultra-short-term (UST) correction with real-time power data. The methodology followed during this thesis was the development of four UST-WPF models for Princess Amalia Wind Farm (PAWP) with a 16 programme time unit (PTU) forecast horizon and a forecast frequency of 1 PTU. Both model 1 and model 2 only use real-time data and are based on a multilayer perceptron (MLP) and a long short-term memory (LSTM) architecture, respectively. The other two proposed models are a multivariate combination of these two respective models with the Eneco model.

The accuracy of the four proposed models was compared to two benchmark models: a Persistence and the Eneco model. Additionally, a novel framework was designed to evaluate the forecast value relative to the Eneco model on a variable forecast horizon. This study indicates that the proposed deep learning models can contribute both in quality and value up to 9 PTUs ahead.

Ultra-Short-Term Wind Power Forecasting
Long Short-Term Memory networks
Multilayer Perceptron
Multi-Step Ahead Wind Forecasting
Persistence

http://resolver.tudelft.nl/uuid:54791037-a0ac-44bb-836a-0ea2c9525a0d

2023-08-18

52.58755, 4.224012

Student theses

master thesis

© 2021 Thom Homsma