Harnessing Recurrent-Based Deep Learning Models for Time Series Photovoltaic Power Forecasting

Mohamed Massaoud; Mohammad Al Shaikh Saleh; Maymouna Ez Eddin; Erchin Serpedin; Ali Ghrayeb; Haitham Abu-Rub

doi:10.1109/IECON51785.2023.10312298

Harnessing Recurrent-Based Deep Learning Models for Time Series Photovoltaic Power Forecasting

Mohamed Massaoud, Mohammad Al Shaikh Saleh, Maymouna Ez Eddin, Erchin Serpedin, Ali Ghrayeb, Haitham Abu-Rub

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Photovoltaic (PV) power is progressively being subsumed into power grids. Consequently, reliable PV power forecasting (PVPF) has become essential to avoid ramp events that can adversely affect the operations of integrated power systems. This article presents a deep-learning-based algorithm for PVPF. The gated recurrent units (GRU) network was implemented to predict the non-linear spatiotemporal correlations of the weather data, leading to higher reliability of the PV stations. Experimental results obtained from actual testing demonstrate the validity of the GRU networks for accurate PVPF, contributing to the efficient operation and management of smart grids and renewable energy systems. The conducted case study shows that the proposed model outperforms bidirectional long short term memory (BiLSTM) and long short term memory (LSTM) models in terms of computation power, root-mean-square error, and mean absolute error metrics.

Original language	English
Title of host publication	IECON 2023 - 49th Annual Conference of the IEEE Industrial Electronics Society
Publisher	IEEE Computer Society
ISBN (Electronic)	9798350331820
DOIs	https://doi.org/10.1109/IECON51785.2023.10312298
Publication status	Published - 2023
Externally published	Yes
Event	49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023 - Singapore, Singapore Duration: 16 Oct 2023 → 19 Oct 2023

Publication series

Name	IECON Proceedings (Industrial Electronics Conference)
ISSN (Print)	2162-4704
ISSN (Electronic)	2577-1647

Conference

Conference	49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023
Country/Territory	Singapore
City	Singapore
Period	16/10/23 → 19/10/23

Keywords

Bidirectional long short-term memory
gated recurrent unit
photovoltaic power forecasting
short-term forecasting
smart grid

Access to Document

10.1109/IECON51785.2023.10312298

Cite this

Massaoud, M., Saleh, M. A. S., Eddin, M. E., Serpedin, E., Ghrayeb, A., & Abu-Rub, H. (2023). Harnessing Recurrent-Based Deep Learning Models for Time Series Photovoltaic Power Forecasting. In IECON 2023 - 49th Annual Conference of the IEEE Industrial Electronics Society (IECON Proceedings (Industrial Electronics Conference)). IEEE Computer Society. https://doi.org/10.1109/IECON51785.2023.10312298

@inproceedings{5699029bbd374e18a5d3ffc9020e1530,

title = "Harnessing Recurrent-Based Deep Learning Models for Time Series Photovoltaic Power Forecasting",

abstract = "Photovoltaic (PV) power is progressively being subsumed into power grids. Consequently, reliable PV power forecasting (PVPF) has become essential to avoid ramp events that can adversely affect the operations of integrated power systems. This article presents a deep-learning-based algorithm for PVPF. The gated recurrent units (GRU) network was implemented to predict the non-linear spatiotemporal correlations of the weather data, leading to higher reliability of the PV stations. Experimental results obtained from actual testing demonstrate the validity of the GRU networks for accurate PVPF, contributing to the efficient operation and management of smart grids and renewable energy systems. The conducted case study shows that the proposed model outperforms bidirectional long short term memory (BiLSTM) and long short term memory (LSTM) models in terms of computation power, root-mean-square error, and mean absolute error metrics.",

keywords = "Bidirectional long short-term memory, gated recurrent unit, photovoltaic power forecasting, short-term forecasting, smart grid",

author = "Mohamed Massaoud and Saleh, {Mohammad Al Shaikh} and Eddin, {Maymouna Ez} and Erchin Serpedin and Ali Ghrayeb and Haitham Abu-Rub",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023 ; Conference date: 16-10-2023 Through 19-10-2023",

year = "2023",

doi = "10.1109/IECON51785.2023.10312298",

language = "English",

series = "IECON Proceedings (Industrial Electronics Conference)",

publisher = "IEEE Computer Society",

booktitle = "IECON 2023 - 49th Annual Conference of the IEEE Industrial Electronics Society",

address = "United States",

}

Massaoud, M, Saleh, MAS, Eddin, ME, Serpedin, E, Ghrayeb, A & Abu-Rub, H 2023, Harnessing Recurrent-Based Deep Learning Models for Time Series Photovoltaic Power Forecasting. in IECON 2023 - 49th Annual Conference of the IEEE Industrial Electronics Society. IECON Proceedings (Industrial Electronics Conference), IEEE Computer Society, 49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023, Singapore, Singapore, 16/10/23. https://doi.org/10.1109/IECON51785.2023.10312298

Harnessing Recurrent-Based Deep Learning Models for Time Series Photovoltaic Power Forecasting. / Massaoud, Mohamed; Saleh, Mohammad Al Shaikh; Eddin, Maymouna Ez et al.
IECON 2023 - 49th Annual Conference of the IEEE Industrial Electronics Society. IEEE Computer Society, 2023. (IECON Proceedings (Industrial Electronics Conference)).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Harnessing Recurrent-Based Deep Learning Models for Time Series Photovoltaic Power Forecasting

AU - Massaoud, Mohamed

AU - Saleh, Mohammad Al Shaikh

AU - Eddin, Maymouna Ez

AU - Serpedin, Erchin

AU - Ghrayeb, Ali

AU - Abu-Rub, Haitham

PY - 2023

Y1 - 2023

N2 - Photovoltaic (PV) power is progressively being subsumed into power grids. Consequently, reliable PV power forecasting (PVPF) has become essential to avoid ramp events that can adversely affect the operations of integrated power systems. This article presents a deep-learning-based algorithm for PVPF. The gated recurrent units (GRU) network was implemented to predict the non-linear spatiotemporal correlations of the weather data, leading to higher reliability of the PV stations. Experimental results obtained from actual testing demonstrate the validity of the GRU networks for accurate PVPF, contributing to the efficient operation and management of smart grids and renewable energy systems. The conducted case study shows that the proposed model outperforms bidirectional long short term memory (BiLSTM) and long short term memory (LSTM) models in terms of computation power, root-mean-square error, and mean absolute error metrics.

AB - Photovoltaic (PV) power is progressively being subsumed into power grids. Consequently, reliable PV power forecasting (PVPF) has become essential to avoid ramp events that can adversely affect the operations of integrated power systems. This article presents a deep-learning-based algorithm for PVPF. The gated recurrent units (GRU) network was implemented to predict the non-linear spatiotemporal correlations of the weather data, leading to higher reliability of the PV stations. Experimental results obtained from actual testing demonstrate the validity of the GRU networks for accurate PVPF, contributing to the efficient operation and management of smart grids and renewable energy systems. The conducted case study shows that the proposed model outperforms bidirectional long short term memory (BiLSTM) and long short term memory (LSTM) models in terms of computation power, root-mean-square error, and mean absolute error metrics.

KW - Bidirectional long short-term memory

KW - gated recurrent unit

KW - photovoltaic power forecasting

KW - short-term forecasting

KW - smart grid

UR - http://www.scopus.com/inward/record.url?scp=85179522951&partnerID=8YFLogxK

U2 - 10.1109/IECON51785.2023.10312298

DO - 10.1109/IECON51785.2023.10312298

M3 - Conference contribution

AN - SCOPUS:85179522951

T3 - IECON Proceedings (Industrial Electronics Conference)

BT - IECON 2023 - 49th Annual Conference of the IEEE Industrial Electronics Society

PB - IEEE Computer Society

T2 - 49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

Y2 - 16 October 2023 through 19 October 2023

ER -

Harnessing Recurrent-Based Deep Learning Models for Time Series Photovoltaic Power Forecasting

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this