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

TL;DR

The 2DXformer model enhances wind power forecasting by explicitly modeling inter-variable relationships and differentiating between endogenous and exogenous variables, leading to improved accuracy on real-world datasets.

Contribution

This paper introduces the 2DXformer, a novel transformer-based model that separately processes and models static, dynamic, and endogenous variables for better wind power prediction.

Findings

Improved forecasting accuracy on large-scale datasets.

Effective modeling of inter-variable relationships.

Better handling of exogenous and endogenous variables.

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: \href{https://github.com/jseaj/2DXformer}{https://github.com/jseaj/2DXformer}.