Daily global solar radiation time series prediction using variational mode decomposition combined with multi-functional recurrent fuzzy neural network and quantile regression forests algorithm

Computing and Communications

Text available via DOI:

https://doi.org/10.1016/j.egyr.2023.10.070
Final published version
Available under license: CC BY: Creative Commons Attribution 4.0 International License

Keywords

Global solar radiation, Meteorological factor, Quantile regression forests, Recurrent fuzzy neural network

View graph of relations

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Daily global solar radiation time series prediction using variational mode decomposition combined with multi-functional recurrent fuzzy neural network and quantile regression forests algorithm. / Abdallah, Mohammed; Mohammadi, Babak; Nasiri, Hamid et al.
In: Energy Reports, Vol. 10, 01.11.2023, p. 4198-4217.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Bibtex

@article{7d90afff96bc4f1a9ac28480faa75bcb,

title = "Daily global solar radiation time series prediction using variational mode decomposition combined with multi-functional recurrent fuzzy neural network and quantile regression forests algorithm",

abstract = "Global solar radiation (GSR) prediction capability with a reliable model and high accuracy is crucial for comprehending hydrological and meteorological systems. It is vital for the production of renewable and clean energy. This research aims to evaluate the performance of combined variational mode decomposition (VMD) with a multi-functional recurrent fuzzy neural network (MFRFNN) and quantile regression forests (QRF) models for GSR prediction in daily scales. The hybrid VMD-MFRFNN and QRF models were compared with standalone MFRFNN, random forest (RF), extreme gradient boosting (XGB), and M5 tree (M5T) models across the Lund and V{\"a}xj{\"o} meteorological stations in Sweden. The meteorological data from 2008 to 2017 were used to train the models, while the prediction accuracy was verified by using the data from 2018 to 2021 under five different input combinations. The various meteorological-based scenarios (including the input are air temperatures (Tmin, Tmax, T), wind speed (WS), relative humidity (RH), sunshine duration (SSH), and maximum possible sunshine duration (N)) were considered as input of predictor models. The current study resulted that the M5T model exhibited higher accuracy than RF and XGB models, while the QRF model showed equivalent performance with the M5T model at both study sites. The MFRFNN model outperformed QRF and M5T models across all input combinations at both study sites. The hybrid VMD-MFRFNN model showed the best performance when fewer input variables (Tmin, Tmax, T, WS at Lund station and Tmin, Tmax, T, WS, SSH, RH at V{\"a}xj{\"o} station) were used for GSR prediction. We conclude that the MFRFNN model best predicts average daily GSR when combining all meteorological variables (Tmin, Tmax, T, WS, SSH, RH, N).",

keywords = "Global solar radiation, Meteorological factor, Quantile regression forests, Recurrent fuzzy neural network",

author = "Mohammed Abdallah and Babak Mohammadi and Hamid Nasiri and Katipoğlu, {Okan Mert} and Abdalla, {Modawy Adam Ali} and Ebadzadeh, {Mohammad Mehdi}",

note = "Publisher Copyright: {\textcopyright} 2023 The Authors",

year = "2023",

month = nov,

day = "1",

doi = "10.1016/j.egyr.2023.10.070",

language = "English",

volume = "10",

pages = "4198--4217",

journal = "Energy Reports",

issn = "2352-4847",

publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Daily global solar radiation time series prediction using variational mode decomposition combined with multi-functional recurrent fuzzy neural network and quantile regression forests algorithm

AU - Abdallah, Mohammed

AU - Mohammadi, Babak

AU - Nasiri, Hamid

AU - Katipoğlu, Okan Mert

AU - Abdalla, Modawy Adam Ali

AU - Ebadzadeh, Mohammad Mehdi

PY - 2023/11/1

Y1 - 2023/11/1

N2 - Global solar radiation (GSR) prediction capability with a reliable model and high accuracy is crucial for comprehending hydrological and meteorological systems. It is vital for the production of renewable and clean energy. This research aims to evaluate the performance of combined variational mode decomposition (VMD) with a multi-functional recurrent fuzzy neural network (MFRFNN) and quantile regression forests (QRF) models for GSR prediction in daily scales. The hybrid VMD-MFRFNN and QRF models were compared with standalone MFRFNN, random forest (RF), extreme gradient boosting (XGB), and M5 tree (M5T) models across the Lund and Växjö meteorological stations in Sweden. The meteorological data from 2008 to 2017 were used to train the models, while the prediction accuracy was verified by using the data from 2018 to 2021 under five different input combinations. The various meteorological-based scenarios (including the input are air temperatures (Tmin, Tmax, T), wind speed (WS), relative humidity (RH), sunshine duration (SSH), and maximum possible sunshine duration (N)) were considered as input of predictor models. The current study resulted that the M5T model exhibited higher accuracy than RF and XGB models, while the QRF model showed equivalent performance with the M5T model at both study sites. The MFRFNN model outperformed QRF and M5T models across all input combinations at both study sites. The hybrid VMD-MFRFNN model showed the best performance when fewer input variables (Tmin, Tmax, T, WS at Lund station and Tmin, Tmax, T, WS, SSH, RH at Växjö station) were used for GSR prediction. We conclude that the MFRFNN model best predicts average daily GSR when combining all meteorological variables (Tmin, Tmax, T, WS, SSH, RH, N).

AB - Global solar radiation (GSR) prediction capability with a reliable model and high accuracy is crucial for comprehending hydrological and meteorological systems. It is vital for the production of renewable and clean energy. This research aims to evaluate the performance of combined variational mode decomposition (VMD) with a multi-functional recurrent fuzzy neural network (MFRFNN) and quantile regression forests (QRF) models for GSR prediction in daily scales. The hybrid VMD-MFRFNN and QRF models were compared with standalone MFRFNN, random forest (RF), extreme gradient boosting (XGB), and M5 tree (M5T) models across the Lund and Växjö meteorological stations in Sweden. The meteorological data from 2008 to 2017 were used to train the models, while the prediction accuracy was verified by using the data from 2018 to 2021 under five different input combinations. The various meteorological-based scenarios (including the input are air temperatures (Tmin, Tmax, T), wind speed (WS), relative humidity (RH), sunshine duration (SSH), and maximum possible sunshine duration (N)) were considered as input of predictor models. The current study resulted that the M5T model exhibited higher accuracy than RF and XGB models, while the QRF model showed equivalent performance with the M5T model at both study sites. The MFRFNN model outperformed QRF and M5T models across all input combinations at both study sites. The hybrid VMD-MFRFNN model showed the best performance when fewer input variables (Tmin, Tmax, T, WS at Lund station and Tmin, Tmax, T, WS, SSH, RH at Växjö station) were used for GSR prediction. We conclude that the MFRFNN model best predicts average daily GSR when combining all meteorological variables (Tmin, Tmax, T, WS, SSH, RH, N).

KW - Global solar radiation

KW - Meteorological factor

KW - Quantile regression forests

KW - Recurrent fuzzy neural network

U2 - 10.1016/j.egyr.2023.10.070

DO - 10.1016/j.egyr.2023.10.070

M3 - Journal article

AN - SCOPUS:85175724063

VL - 10

SP - 4198

EP - 4217

JO - Energy Reports

JF - Energy Reports

SN - 2352-4847

ER -

Research

Links

Text available via DOI:

Keywords