A transformer-based wind power forecasting model with multi-scale power difference embedding

Effective engineering management of wind power projects requires balancing cost-efficiency with sustainable development through comprehensive resource optimization. While wind power forecasting (WPF) improves operational stability and economic performance via generation prediction, current methods face persistent challenges in responding to short-term power fluctuations and capturing long-term weather patterns. This study presents a novel multiscale prediction model combining power difference (PD) features with a hybrid Long short-term memory (LSTM)-Transformer architecture. The proposed approach employs differential operations to extract physically meaningful dynamic features, followed by a cascaded deep learning framework: bidirectional LSTM processes hourly variations, Transformer encoders learn inter-day dependencies, and positional encoding maintains temporal coherence. Experimental results show significant improvements over baseline models, with 25.81% mean squared error (MAE), 21.05% root mean squared error (RMSE), and 23.44% R-square (R2) gains versus standalone LSTM, and 28.13% MAE, 26.83% RMSE, and 33.90% R2 enhancements compared to pure Transformer. The integration of physical mechanisms with multiscale temporal modelling demonstrates superior prediction accuracy and system robustness for renewable energy applications.

• Publication year

  2025

• Venue

  Journal of Physics: Conference Series

• Publication date

  2025-08-01

• Fields of study

  Physics, Engineering, Environmental Science

• Identifiers
  DOI 10.1088/1742-6596/3065/1/012034
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Review of several key processes in wind power forecasting: Mathematical formulations, scientific problems, and logical relations

  2025cited by this paper
• Powerformer: A temporal-based transformer model for wind power forecasting

  2024cited by this paper
• Short-term wind power forecasting based on multivariate/multi-step LSTM with temporal feature attention mechanism

  2024cited by this paper
• Wind power forecasting system with data enhancement and algorithm improvement

  2024cited by this paper
• A novel meta-learning approach for few-shot short-term wind power forecasting

  2024cited by this paper
• Wind power forecasting method of large-scale wind turbine clusters based on DBSCAN clustering and an enhanced hunter-prey optimization algorithm

  2024cited by this paper
• A novel temporal-spatial graph neural network for wind power forecasting considering blockage effects

  2024cited by this paper
• A review of short-term wind power generation forecasting methods in recent technological trends

  2024cited by this paper
• Decoding of movement-related cortical potentials at different speeds

  2024cited by this paper
• A privacy-preserving framework integrating federated learning and transfer learning for wind power forecasting

  2023cited by this paper
• STMI: Stiffness Estimation Method Based on sEMG-Driven Model for Elbow Joint

  2023cited by this paper
• Ultra-short-term wind power forecasting based on personalized robust federated learning with spatial collaboration

  2023cited by this paper
• A high-accuracy hybrid method for short-term wind power forecasting

  2022cited by this paper
• Toward Generalization of sEMG-Based Pattern Recognition: A Novel Feature Extraction for Gesture Recognition

  2022cited by this paper
• Short-term wind power forecasting based on meteorological feature extraction and optimization strategy

  2021cited by this paper
• Deep belief network based k-means cluster approach for short-term wind power forecasting

  2018influential reference

• Decomposition-Driven Transformer for Accurate and Trend-Aware Wind Power Prediction

  2025cites this paper