کنفرانس بین المللی فناوری و مدیریت انرژی

صفحه اصلی / نهمین کنفرانس بین المللی فناوری و مدیریت انرژی

Wind Farm Power Prediction with Transformer Encoder

نویسندگان :

Elman Ghazaei¹ Omid Feizi² Amir A. Ghavifekr³ Mina Salim⁴ Armin Hassanzadeh⁵

1- University of Tabriz 2- University of Tabriz 3- University of Tabriz 4- University of Tabriz 5- University of Tabriz

کلمات کلیدی :

Wind Turbine،Deep Learning،Power Prediction،Transformer Encoder،Wind Farm

چکیده :

The increasing utilization of renewable energy sources, such as wind power, into the electrical grid, requires accurate prediction methods to improve grid reliability and stability. This paper presents a novel approach for wind farm power prediction using Transformer Encoder structure as a cutting-edge deep learning model. The Transformer Encoder demonstrates promising potentials in identifying temporal dependencies and spatial correlations inherent in wind farm data. The proposed model learns complex patterns in wind speed, direction, and other pertinent meteorological features by utilizing the self-attention mechanism of Transformer Encoders to efficiently capture long-range dependencies within time-series data. To validate the performance of the proposed model, experiments are carried out on real-world wind farm datasets, comparing the Transformer Encoder-based approach with conventional forecasting methods and other deep learning models. The outcomes demonstrate the superiority of the proposed model in terms of accuracy, robustness, and adaptability to varying environmental conditions.