2DXformer: Dual Transformers for Wind Power Forecasting with Dual Exogenous Variables

2025/05/02 by Yajuan Zhang, Zhang, Yajuan, Yule Yan +6
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #Energy Load and Power Forecasting #FOS: Computer and information sciences #Image and Signal Denoising Methods #Machine Learning (cs.LG) #Neural Networks and Applications

paper · pdf · doi:10.48550/arxiv.2505.01286

openalex publication_date 2025/05/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Accurate wind power forecasting can help formulate scientific dispatch plans, which is of great significance for maintaining the safety, stability, and efficient operation of the power system. In recent years, wind power forecasting methods based on deep learning have focused on extracting the spatiotemporal correlations among data, achieving significant improvements in forecasting accuracy. However, they exhibit two limitations. First, there is a lack of modeling for the inter-variable relationships, which limits the accuracy of the forecasts. Second, by treating endogenous and exogenous variables equally, it leads to unnecessary interactions between the endogenous and exogenous variables, increasing the complexity of the model. In this paper, we propose the 2DXformer, which, building upon the previous work's focus on spatiotemporal correlations, addresses the aforementioned two limitations. Specifically, we classify the inputs of the model into three types: exogenous static variables, exogenous dynamic variables, and endogenous variables. First, we embed these variables as variable tokens in a channel-independent manner. Then, we use the attention mechanism to capture the correlations among exogenous variables. Finally, we employ a multi-layer perceptron with residual connections to model the impact of exogenous variables on endogenous variables. Experimental results on two real-world large-scale datasets indicate that our proposed 2DXformer can further improve the performance of wind power forecasting. The code is available in this repository: \hrefhttps://github.com/jseaj/2DXformerhttps://github.com/jseaj/2DXformer.

Citations

• TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables
• Long-term Wind Power Forecasting with Hierarchical Spatial-Temporal Transformer
• Long-term Forecasting with TiDE: Time-series Dense Encoder
• Spatio-Temporal Meta-Graph Learning for Traffic Forecasting
• Short-Term Power Prediction for Renewable Energy Using Hybrid Graph Convolutional Network and Long Short-Term Memory Approach
• Deep Spatio-Temporal Wind Power Forecasting
• Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting
• Scene Learning: Deep Convolutional Networks For Wind Power Prediction by Embedding Turbines into Grid Space
• Attention Is All You Need
• Fast R-CNN
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation

Related

• Explainable Modeling for Wind Power Forecasting: A Glass-Box Approach with High Accuracy
• DEWP: Deep Expansion Learning for Wind Power Forecasting
• Enhancing Wind Power Forecast Precision via Multi-head Attention Transformer: An Investigation on Single-step and Multi-step Forecasting
• Deep Spatio-Temporal Wind Power Forecasting
• Deep Generative Methods for Producing Forecast Trajectories in Power Systems