Spatio-Temporal Wind Speed Forecasting using Graph Networks and Novel Transformer Architectures

Abstract

This study focuses on multi-step spatio-temporal wind speed forecasting for the Norwegian continental shelf. The study aims to leverage spatial dependencies through the relative physical location of different measurement stations to improve local wind forecasts. Our multi-step forecasting models produce either 10-minute, 1- or 4-hour forecasts, with 10-minute resolution, meaning that the models produce more informative time series for predicted future trends. A graph neural network (GNN) architecture was used to extract spatial dependencies, with different update functions to learn temporal correlations. These update functions were implemented using different neural network architectures. One such architecture, the Transformer, has become increasingly popular for sequence modelling in recent years. Various alterations have been proposed to better facilitate time series forecasting, of which this study focused on the Informer, LogSparse Transformer and Autoformer. This is the first time the LogSparse Transformer and Autoformer have been applied to wind forecasting and the first time any of these or the Informer have been formulated in a spatio-temporal setting for wind forecasting. By comparing against spatio-temporal Long Short-Term Memory (LSTM) and Multi-Layer Perceptron (MLP) models, the study showed that the models using the altered Transformer architectures as update functions in GNNs were able to outperform these. Furthermore, we propose the Fast Fourier Transformer (FFTransformer), which is a novel Transformer architecture based on signal decomposition and consists of two separate streams that analyse the trend and periodic components separately. The FFTransformer and Autoformer were found to achieve superior results for the 10-minute and 1-hour ahead forecasts, with the FFTransformer significantly outperforming all other models for the 4-hour ahead forecasts.

arXiv comment(Please cite this version): https://doi.org/10.1016/j.apenergy.2022.120565 Code Available at https://github.com/LarsBentsen/FFTransformer

References in corpus (5)

• Neural Machine Translation by Jointly Learning to Align and Translate
• WaveNet: A Generative Model for Raw Audio
• Longformer: The Long-Document Transformer
• Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
• FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting

Cited by in corpus (3)

• A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classification
• Local Off-Grid Weather Forecasting with Multi-Modal Earth Observation Data
• Integrating the Expected Future in Load Forecasts with Contextually Enhanced Transformer Models