Hybrid deep CNN-SVR algorithm for solar radiation prediction problems in Queensland, Australia

Ghimire, Sujan and Bhandari, Binayak and Casillas-Perez, David and Deo, Ravinesh C. ORCID: https://orcid.org/0000-0002-2290-6749 and Salcedo-Sanz, Sancho (2022) Hybrid deep CNN-SVR algorithm for solar radiation prediction problems in Queensland, Australia. Engineering Applications of Artificial Intelligence, 112:104860. pp. 1-26. ISSN 0952-1976

[img]
Preview
Text (Published Version)
1-s2.0-S0952197622001099-main.pdf
Available under License Creative Commons Attribution Non-commercial No Derivatives 4.0.

Download (5MB) | Preview

Abstract

This study proposes a new hybrid deep learning (DL) model, the called CSVR, for Global Solar Radiation (GSR) predictions by integrating Convolutional Neural Network (CNN) with Support Vector Regression (SVR) approach. First, the CNN algorithm is used to extract local patterns as well as common features that occur recurrently in time series data at different intervals. Then, the SVR is subsequently adopted to replace the fully connected CNN layers to predict the daily GSR time series data at six solar farms in Queensland, Australia. To develop the hybrid CSVR model, we adopt the most pertinent meteorological variables from Global Climate Model and Scientific Information for Landowners database. From a pool of Global Climate Models variables and ground-based observations, the optimal features are selected through a metaheuristic Feature Selection algorithm, an Atom Search Optimization method. The hyperparameters of the proposed CSVR are optimized by mean of the HyperOpt method, and the overall performance of the objective algorithm is benchmarked against eight alternative DL methods, and some of the other Machine Learning approaches (LSTM, DBN, RBF, BRF, MARS, WKNNR, GPML and M5TREE) methods. The results obtained shows that the proposed CSVR model can offer several predictive advantages over the alternative DL models, as well as the conventional ML models. Specifically, we note that the CSVR model recorded a root mean square error/mean absolute error ranging between 2.172–3.305 MJ m2/1.624–2.370 MJ m2 over the six tested solar farms compared to 2.514–3.879 MJ m2/1.939–2.866 MJ m2 from alternative ML and DL algorithms. Consistent with this predicted error, the correlation between the measured and the predicted GSR, including the Willmott’s, Nash-Sutcliffe’s coefficient and Legates & McCabe’s Index was relatively higher for the proposed CSVR model compared to other DL and Machine Learning methods for all of the study sites. Accordingly, this study advocates the merits of CSVR model to provide a viable alternative to accurately predict GSR for renewable energy exploitation, energy demand or other forecasting-based applications.


Statistics for USQ ePrint 48583
Statistics for this ePrint Item
Item Type: Article (Commonwealth Reporting Category C)
Refereed: Yes
Item Status: Live Archive
Faculty/School / Institute/Centre: Current – Faculty of Health, Engineering and Sciences - School of Mathematics, Physics and Computing (1 Jan 2022 -)
Faculty/School / Institute/Centre: Current – Faculty of Health, Engineering and Sciences - School of Mathematics, Physics and Computing (1 Jan 2022 -)
Date Deposited: 26 May 2022 03:56
Last Modified: 26 May 2022 03:56
Uncontrolled Keywords: Convolutional Neural Networks; Support Vector Regression; Solar energy prediction; Feature selection; Hybrid models
Fields of Research (2020): 46 INFORMATION AND COMPUTING SCIENCES > 4602 Artificial intelligence > 460207 Modelling and simulation
40 ENGINEERING > 4008 Electrical engineering > 400803 Electrical energy generation (incl. renewables, excl. photovoltaics)
Socio-Economic Objectives (2020): 28 EXPANDING KNOWLEDGE > 2801 Expanding knowledge > 280115 Expanding knowledge in the information and computing sciences
Funding Details:
Identification Number or DOI: https://doi.org/10.1016/j.engappai.2022.104860
URI: http://eprints.usq.edu.au/id/eprint/48583

Actions (login required)

View Item Archive Repository Staff Only