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

• URL: http://arxiv.org/abs/2505.01286v1
• Date: Fri, 02 May 2025 14:00:48 GMT
• Title: 2DXformer: Dual Transformers for Wind Power Forecasting with Dual Exogenous Variables
• Authors: Yajuan Zhang, Jiahai Jiang, Yule Yan, Liang Yang, Ping Zhang,
• Abstract summary: Wind power forecasting methods based on deep learning have focused on extracting correlations among data, achieving significant improvements in forecasting accuracy.<n>However, there is a lack of modeling for the inter-temporal relationships, which limits the accuracy of the forecasts.<n>We propose the 2DXformer, which builds upon the previous work's focus on windtemporal correlations, addresses the aforementioned two limitations.
• Score: 8.401357727849419
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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}.

Related papers

• Met$^2$Net: A Decoupled Two-Stage Spatio-Temporal Forecasting Model for Complex Meteorological Systems [9.177158814568887]
  extreme weather events due to global climate change urges accurate weather prediction.<n>We propose an implicit two-stage training method, configuring separate encoders and decoders for each variable.<n>Our method reduces the MSE for near-surface air temperature and relative humidity predictions by 28.82% and 23.39%, respectively.
  arXiv  Detail & Related papers  (2025-07-23T04:26:56Z)
• ExoTST: Exogenous-Aware Temporal Sequence Transformer for Time Series Prediction [11.511830352094353]
  We propose ExoTST, a transformer-based framework for time series prediction. To integrate past and current variables, ExoTST introduces a novel cross-temporal modality fusion module. Experiments on real-world carbon flux datasets and time series benchmarks demonstrate ExoTST's superior performance.
  arXiv  Detail & Related papers  (2024-10-16T03:04:37Z)
• VCformer: Variable Correlation Transformer with Inherent Lagged Correlation for Multivariate Time Series Forecasting [1.5165632546654102]
  We propose Variable Correlation Transformer (VCformer) to mine the correlations among variables. VCA calculates and integrates the cross-correlation scores corresponding to different lags between queries and keys. Inspired by Koopman dynamics theory, we also develop Koopman Temporal Detector (KTD) to better address the non-stationarity in time series.
  arXiv  Detail & Related papers  (2024-05-19T07:39:22Z)
• TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables [75.83318701911274]
  TimeXer ingests external information to enhance the forecasting of endogenous variables. TimeXer achieves consistent state-of-the-art performance on twelve real-world forecasting benchmarks.
  arXiv  Detail & Related papers  (2024-02-29T11:54:35Z)
• Confident Adaptive Language Modeling [95.45272377648773]
  CALM is a framework for dynamically allocating different amounts of compute per input and generation timestep. We demonstrate the efficacy of our framework in reducing compute -- potential speedup of up to $times 3$ -- while provably maintaining high performance.
  arXiv  Detail & Related papers  (2022-07-14T17:00:19Z)
• Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition [62.83832841523525]
  We propose a fast and accurate parallel transformer, termed Paraformer. It accurately predicts the number of output tokens and extract hidden variables. It can attain comparable performance to the state-of-the-art AR transformer, with more than 10x speedup.
  arXiv  Detail & Related papers  (2022-06-16T17:24:14Z)
• Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression [151.3826781154146]
  latent variables with priors and hyperpriors is an essential problem in variational image compression. We find inter-correlations and intra-correlations exist when observing latent variables in a vectorized perspective. Our model has better rate-distortion performance and an impressive $3.18times$ compression speed up.
  arXiv  Detail & Related papers  (2022-03-21T11:44:17Z)
• Interpretable Latent Variables in Deep State Space Models [4.884336328409872]
  We introduce a new version of deep state-space models (DSSMs) that combines a recurrent neural network with a state-space framework to forecast time series data. The model estimates the observed series as functions of latent variables that evolve non-linearly through time.
  arXiv  Detail & Related papers  (2022-03-03T23:10:58Z)
• Encoding Causal Macrovariables [0.0]
  In many scientific disciplines, coarse-grained causal models are used to explain and predict the dynamics of more fine-grained systems. This work introduces a novel algorithmic approach that is inspired by a new characterisation of causal macrovariables as information bottlenecks between microstates.
  arXiv  Detail & Related papers  (2021-11-29T17:25:11Z)
• X-model: Improving Data Efficiency in Deep Learning with A Minimax Model [78.55482897452417]
  We aim at improving data efficiency for both classification and regression setups in deep learning. To take the power of both worlds, we propose a novel X-model. X-model plays a minimax game between the feature extractor and task-specific heads.
  arXiv  Detail & Related papers  (2021-10-09T13:56:48Z)
• Multivariate Probabilistic Regression with Natural Gradient Boosting [63.58097881421937]
  We propose a Natural Gradient Boosting (NGBoost) approach based on nonparametrically modeling the conditional parameters of the multivariate predictive distribution. Our method is robust, works out-of-the-box without extensive tuning, is modular with respect to the assumed target distribution, and performs competitively in comparison to existing approaches.
  arXiv  Detail & Related papers  (2021-06-07T17:44:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.