Short-Term Wind Speed and Temperature Forecasting Model Based on Gated Recurrent Unit Neural Networks

Alharbi, Fahad and Csala, Dénes (2021) Short-Term Wind Speed and Temperature Forecasting Model Based on Gated Recurrent Unit Neural Networks. In: Proceedings - 2021 IEEE 3rd Global Power, Energy and Communication Conference, GPECOM 2021 :. Proceedings - 2021 IEEE 3rd Global Power, Energy and Communication Conference, GPECOM 2021 . IEEE, pp. 142-147. ISBN 9781665435130

[thumbnail of Short-Term Wind Speed and Temperature Forecasting]
Text (Short-Term Wind Speed and Temperature Forecasting)
Short_Term_Wind_Speed_and_Temperature_Forecasting.pdf - Accepted Version
Available under License Creative Commons Attribution-NonCommercial.

Download (896kB)

Abstract

Wind energy generation fluctuations and intermittency issues create inefficiency and instability in power management. The recurrent neural networks (RNNs) prediction approaches are an essential technology that can improve wind power generation and assist in energy management and power systems’ performance. In this paper, a prediction model based on Gated Recurrent Unit (GRU) neural networks is proposed to predict wind speed and temperature values one week ahead in the future at hourly intervals. The GRU prediction model automatically learnt the features, used fewer training parameters, and required a shorter time to train compared to other types of RNNs. The GRU model was designed to predict 169 hours ahead as a short-term period of wind speed and temperature values based on 36 years of hourly historical data (1 January 1985 to 6 June 2021) collected from Dumat al-Jandal city. The findings notably indicate that the GRU model has promising performance with significant prediction accuracies in terms of overfitting, reliability, resolution, efficiency, and generalizable processes. The GRU model is characterized by its good performance and influential evaluation error metrics for wind speed and temperature values.

Item Type:
Contribution in Book/Report/Proceedings
Additional Information:
©2021 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
ID Code:
164308
Deposited By:
Deposited On:
18 Nov 2022 11:15
Refereed?:
Yes
Published?:
Published
Last Modified:
18 Mar 2024 00:12