Forecast of Wind Speed Using GRU Neural Network in Tetouan City

EasyChair Preprint no. 11968

Abstract

Wind speed prediction is crucial for efficient electricity production from wind energy sources. Previous methods, particularly artificial intelligence techniques, have been established for wind speed prediction. This study employs a Gated Recurrent Unit (GRU) model to predict daily wind speeds in Tetouan City northern Morocco, leveraging five years of historical meteorological data.

We aim to develop a reliable forecasting tool that enhances our understanding of wind patterns in the region, contributing to more efficient energy management."

Utilizing the MATLAB interface and the Adam optimization algorithm, the GRU is trained to ensure robust performance.

Performance metrics, including Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and the correlation coefficient (R), were calculated to assess the accuracy of the forecasting model. The achieved values for MSE, RMSE, and R stand at [insert values here]. These metrics demonstrate the effectiveness of the GRU model in providing precise wind speed predictions.

Keyphrases: Artificial Neural Network, GRU neural network, Optimizations algorithm, RNN neural network, Wind speed prediction

@Booklet{EasyChair:11968,
  author = {Wissal Masmoudi and Abdelouahed Djebli},
  title = {Forecast of Wind Speed Using GRU Neural Network in Tetouan City},
  howpublished = {EasyChair Preprint no. 11968},

  year = {EasyChair, 2024}}