Home > Research > Publications & Outputs > Short-Term Wind Speed and Temperature Forecasti...

Research

Electronic data

Links

Text available via DOI:

View graph of relations

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

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

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

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Alharbi, F & Csala, D 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. https://doi.org/10.1109/GPECOM52585.2021.9587479

APA

Alharbi, F., & Csala, D. (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 (pp. 142-147). (Proceedings - 2021 IEEE 3rd Global Power, Energy and Communication Conference, GPECOM 2021). IEEE. https://doi.org/10.1109/GPECOM52585.2021.9587479

Vancouver

Alharbi F, Csala D. 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. IEEE. 2021. p. 142-147. (Proceedings - 2021 IEEE 3rd Global Power, Energy and Communication Conference, GPECOM 2021). doi: 10.1109/GPECOM52585.2021.9587479

Author

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

Bibtex

@inproceedings{51993b4d648045b9be24fb51af3f9619,
title = "Short-Term Wind Speed and Temperature Forecasting Model Based on Gated Recurrent Unit Neural Networks",
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{\textquoteright} 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. ",
author = "Fahad Alharbi and D{\'e}nes Csala",
note = "{\textcopyright}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. ",
year = "2021",
month = nov,
day = "13",
doi = "10.1109/GPECOM52585.2021.9587479",
language = "English",
isbn = "9781665435130",
series = "Proceedings - 2021 IEEE 3rd Global Power, Energy and Communication Conference, GPECOM 2021",
publisher = "IEEE",
pages = "142--147",
booktitle = "Proceedings - 2021 IEEE 3rd Global Power, Energy and Communication Conference, GPECOM 2021",

}

RIS

TY - GEN

T1 - Short-Term Wind Speed and Temperature Forecasting Model Based on Gated Recurrent Unit Neural Networks

AU - Alharbi, Fahad

AU - Csala, Dénes

N1 - ©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.

PY - 2021/11/13

Y1 - 2021/11/13

N2 - 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.

AB - 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.

U2 - 10.1109/GPECOM52585.2021.9587479

DO - 10.1109/GPECOM52585.2021.9587479

M3 - Conference contribution/Paper

SN - 9781665435130

T3 - Proceedings - 2021 IEEE 3rd Global Power, Energy and Communication Conference, GPECOM 2021

SP - 142

EP - 147

BT - Proceedings - 2021 IEEE 3rd Global Power, Energy and Communication Conference, GPECOM 2021

PB - IEEE

ER -