Comparison between GRU and BP Neural Networks for Short-Term Prediction of Solar Irradiance

Zhou Zhenzhen; Song Yunhai; He Sen; Huang Heyan; He Yuhao; Zhou Shaohui

doi:10.1109/ICCCBDA56900.2023.10154822

Comparison between GRU and BP Neural Networks for Short-Term Prediction of Solar Irradiance

Zhou Zhenzhen^*
, Song Yunhai
, He Sen
, Huang Heyan
, He Yuhao
, Zhou Shaohui

^*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

In this study, we present a data-driven approach for predicting solar irradiance by applying dimensionality reduction techniques to a dataset comprising of ground meteorological station data and FY-4A remote sensing data collected from January 1st to December 31st, 2018. Specifically, we use Principal Component Analysis (PCA) to reduce the dimensionality of the dataset. Next, we employ a Gated Recurrent Unit (GRU) neural network-based short-term irradiance prediction model to realize the short-term prediction of solar irradiance. We then evaluate the performance of the GRU model by comparing its prediction results with those obtained using a traditional Backpropagation (BP) neural network model with measured solar irradiance. The results indicate that the root mean square error (RMSE) of the GRU neural network model is 41% lower than that of the BP neural network model, indicating the improved performance of the proposed model.

Original language	English
Title of host publication	2023 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	605-609
Number of pages	5
ISBN (Electronic)	9781665455336
DOIs	https://doi.org/10.1109/ICCCBDA56900.2023.10154822
Publication status	Published - 2023
Externally published	Yes
Event	8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023 - Chengdu, China Duration: 26 Apr 2023 → 28 Apr 2023

Publication series

Name	2023 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023

Conference

Conference	8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023
Country/Territory	China
City	Chengdu
Period	26/04/23 → 28/04/23

Keywords

BP neural network
GRU neural network
PCA dimension reduction
solar irradiance prediction

Access to Document

10.1109/ICCCBDA56900.2023.10154822

Cite this

Zhenzhen, Z., Yunhai, S., Sen, H., Heyan, H., Yuhao, H., & Shaohui, Z. (2023). Comparison between GRU and BP Neural Networks for Short-Term Prediction of Solar Irradiance. In 2023 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023 (pp. 605-609). (2023 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCCBDA56900.2023.10154822

Zhenzhen, Zhou ; Yunhai, Song ; Sen, He et al. / Comparison between GRU and BP Neural Networks for Short-Term Prediction of Solar Irradiance. 2023 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 605-609 (2023 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023).

@inproceedings{b94480f234bd49e391121539ddecc2b9,

title = "Comparison between GRU and BP Neural Networks for Short-Term Prediction of Solar Irradiance",

abstract = "In this study, we present a data-driven approach for predicting solar irradiance by applying dimensionality reduction techniques to a dataset comprising of ground meteorological station data and FY-4A remote sensing data collected from January 1st to December 31st, 2018. Specifically, we use Principal Component Analysis (PCA) to reduce the dimensionality of the dataset. Next, we employ a Gated Recurrent Unit (GRU) neural network-based short-term irradiance prediction model to realize the short-term prediction of solar irradiance. We then evaluate the performance of the GRU model by comparing its prediction results with those obtained using a traditional Backpropagation (BP) neural network model with measured solar irradiance. The results indicate that the root mean square error (RMSE) of the GRU neural network model is 41\% lower than that of the BP neural network model, indicating the improved performance of the proposed model.",

keywords = "BP neural network, GRU neural network, PCA dimension reduction, solar irradiance prediction",

author = "Zhou Zhenzhen and Song Yunhai and He Sen and Huang Heyan and He Yuhao and Zhou Shaohui",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023 ; Conference date: 26-04-2023 Through 28-04-2023",

year = "2023",

doi = "10.1109/ICCCBDA56900.2023.10154822",

language = "English",

series = "2023 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "605--609",

booktitle = "2023 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023",

address = "United States",

}

Zhenzhen, Z, Yunhai, S, Sen, H, Heyan, H, Yuhao, H & Shaohui, Z 2023, Comparison between GRU and BP Neural Networks for Short-Term Prediction of Solar Irradiance. in 2023 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023. 2023 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023, Institute of Electrical and Electronics Engineers Inc., pp. 605-609, 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023, Chengdu, China, 26/04/23. https://doi.org/10.1109/ICCCBDA56900.2023.10154822

Comparison between GRU and BP Neural Networks for Short-Term Prediction of Solar Irradiance. / Zhenzhen, Zhou; Yunhai, Song; Sen, He et al.
2023 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 605-609 (2023 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023).

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

TY - GEN

T1 - Comparison between GRU and BP Neural Networks for Short-Term Prediction of Solar Irradiance

AU - Zhenzhen, Zhou

AU - Yunhai, Song

AU - Sen, He

AU - Heyan, Huang

AU - Yuhao, He

AU - Shaohui, Zhou

PY - 2023

Y1 - 2023

N2 - In this study, we present a data-driven approach for predicting solar irradiance by applying dimensionality reduction techniques to a dataset comprising of ground meteorological station data and FY-4A remote sensing data collected from January 1st to December 31st, 2018. Specifically, we use Principal Component Analysis (PCA) to reduce the dimensionality of the dataset. Next, we employ a Gated Recurrent Unit (GRU) neural network-based short-term irradiance prediction model to realize the short-term prediction of solar irradiance. We then evaluate the performance of the GRU model by comparing its prediction results with those obtained using a traditional Backpropagation (BP) neural network model with measured solar irradiance. The results indicate that the root mean square error (RMSE) of the GRU neural network model is 41% lower than that of the BP neural network model, indicating the improved performance of the proposed model.

AB - In this study, we present a data-driven approach for predicting solar irradiance by applying dimensionality reduction techniques to a dataset comprising of ground meteorological station data and FY-4A remote sensing data collected from January 1st to December 31st, 2018. Specifically, we use Principal Component Analysis (PCA) to reduce the dimensionality of the dataset. Next, we employ a Gated Recurrent Unit (GRU) neural network-based short-term irradiance prediction model to realize the short-term prediction of solar irradiance. We then evaluate the performance of the GRU model by comparing its prediction results with those obtained using a traditional Backpropagation (BP) neural network model with measured solar irradiance. The results indicate that the root mean square error (RMSE) of the GRU neural network model is 41% lower than that of the BP neural network model, indicating the improved performance of the proposed model.

KW - BP neural network

KW - GRU neural network

KW - PCA dimension reduction

KW - solar irradiance prediction

UR - https://www.scopus.com/pages/publications/85164737113

U2 - 10.1109/ICCCBDA56900.2023.10154822

DO - 10.1109/ICCCBDA56900.2023.10154822

M3 - Conference contribution

AN - SCOPUS:85164737113

T3 - 2023 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023

SP - 605

EP - 609

BT - 2023 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023

Y2 - 26 April 2023 through 28 April 2023

ER -

Zhenzhen Z, Yunhai S, Sen H, Heyan H, Yuhao H, Shaohui Z. Comparison between GRU and BP Neural Networks for Short-Term Prediction of Solar Irradiance. In 2023 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 605-609. (2023 8th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2023). doi: 10.1109/ICCCBDA56900.2023.10154822

Comparison between GRU and BP Neural Networks for Short-Term Prediction of Solar Irradiance

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this