Fast-Powerformer: A Memory-Efficient Transformer for Accurate Mid-Term Wind Power Forecasting

2025-04-15

AI Summary

To address the challenge of simultaneously achieving high accuracy and low computational overhead in medium-term wind power forecasting, this paper proposes Fast-Powerformer—a lightweight and efficient Transformer-based model. Methodologically, it introduces a novel input transposition mechanism tailored to the temporal characteristics of wind power series; designs a frequency-enhanced channel attention module (FECAM) to improve meteorological feature modeling; and integrates lightweight LSTM embeddings with Reformer’s locality-sensitive hashing (LSH) attention to substantially reduce memory footprint and computational complexity. Extensive experiments on multiple real-world wind farm datasets demonstrate that Fast-Powerformer outperforms state-of-the-art methods in prediction accuracy, achieves a 3.2× speedup in inference latency, and reduces GPU memory consumption by 57%, thereby enabling robust real-time deployment.

Technology Category

• Machine Learning: Hardware-aware ML
• Natural Language Processing: Learning & Optimization for NLP
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Wind power forecasting (WPF), as a significant research topic within renewable energy, plays a crucial role in enhancing the security, stability, and economic operation of power grids. However, due to the high stochasticity of meteorological factors (e.g., wind speed) and significant fluctuations in wind power output, mid-term wind power forecasting faces a dual challenge of maintaining high accuracy and computational efficiency. To address these issues, this paper proposes an efficient and lightweight mid-term wind power forecasting model, termed Fast-Powerformer. The proposed model is built upon the Reformer architecture, incorporating structural enhancements such as a lightweight Long Short-Term Memory (LSTM) embedding module, an input transposition mechanism, and a Frequency Enhanced Channel Attention Mechanism (FECAM). These improvements enable the model to strengthen temporal feature extraction, optimize dependency modeling across variables, significantly reduce computational complexity, and enhance sensitivity to periodic patterns and dominant frequency components. Experimental results conducted on multiple real-world wind farm datasets demonstrate that the proposed Fast-Powerformer achieves superior prediction accuracy and operational efficiency compared to mainstream forecasting approaches. Furthermore, the model exhibits fast inference speed and low memory consumption, highlighting its considerable practical value for real-world deployment scenarios.

Problem

• Addresses mid-term wind power forecasting accuracy and efficiency
• Reduces computational complexity in transformer-based forecasting models
• Enhances sensitivity to periodic patterns in wind data

Innovation

• Lightweight LSTM embedding module
• Input transposition mechanism
• Frequency Enhanced Channel Attention Mechanism