WPFormer: A spatial-temporal graph transformer with auto-correlation for wind power forecasting

The development and utilization of clean energy have been an important demand, with wind power standing out as a representative source due to its convenience and well-established technology. Accurate wind power forecasting holds immense significance as it facilitates the development of future genera...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on sustainable energy 2024-10, p.1-13
Main Authors: Liang, Xuefeng, Gu, Qingshui, You, Xiaochuan
Format: Article
Language:English
Subjects:
Accuracy
anomaly detection
Autoregressive processes
Data models
Forecasting
graph transformer
Predictive models
spatio-temporal model
Transformers
Wind forecasting
Wind power forecasting
Wind power generation
Wind speed
Wind turbines
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The development and utilization of clean energy have been an important demand, with wind power standing out as a representative source due to its convenience and well-established technology. Accurate wind power forecasting holds immense significance as it facilitates the development of future generation plans, enhances the economy and reliability of power systems, and promotes the increased utilization of clean energy. However, an abundance of anomalous data stems from harsh turbine environments. The interplay among natural wind patterns, artificial interventions, and turbine states results in poor cyclicality and significant volatility in wind power generation. To address these challenges, we propose the WPFormer framework. Within this framework, we have designed a W ind pow E r D ual-stream S coring model (WEDS), a semi-supervised learning model based on wind power curves, tasked with anomaly detection and data repair. A F eature s E lection metho D based on the S elf-attention mechanism, known as FEDS, is also proposed for identifying valuable features. Furthermore, the spatial information of the wind turbines is introduced, and multiple series decomposition with autocorrelation and multi-headed attention is used to learn the expected prediction behind the randomness, overcome the weak periodicity, and predict the long-term significant volatility trend. Extensive experiments on real-world datasets demonstrate that WPFormer achieves state-of-the-art performance.
ISSN:1949-3029
1949-3037
DOI:10.1109/TSTE.2024.3477288