Next Article in Journal
Distributed Integral Convex Optimization-Based Current Control for Power Loss Optimization in Direct Current Microgrids
Previous Article in Journal
Environmental Protection Tax and Energy Efficiency: Evidence from Chinese City-Level Data
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Forecasting of Solar Power Using GRU–Temporal Fusion Transformer Model and DILATE Loss Function

by
Fatma Mazen Ali Mazen
1,*,†,
Yomna Shaker
1,2,† and
Rania Ahmed Abul Seoud
1,†
1
Electrical Engineering Department, Faculty of Engineering, Fayoum University, Fayoum 63514, Egypt
2
Engineering Department, University of Science and Technology of Fujairah (USTF), Fujairah 2202, United Arab Emirates
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Energies 2023, 16(24), 8105; https://doi.org/10.3390/en16248105
Submission received: 5 November 2023 / Revised: 3 December 2023 / Accepted: 11 December 2023 / Published: 17 December 2023
(This article belongs to the Section A2: Solar Energy and Photovoltaic Systems)

Abstract

Solar power is a clean and sustainable energy source that does not emit greenhouse gases or other atmospheric pollutants. The inherent variability in solar energy due to random fluctuations introduces novel attributes to the power generation and load dynamics of the grid. Consequently, there has been growing attention to developing an accurate forecast model using various machine and deep learning techniques. Temporal attention mechanisms enable the model to concentrate on the critical components of the input sequence at each time step, thereby enhancing the accuracy of the prediction. The suggested GRU–temporal fusion transformer (GRU-TFT) model was trained and validated employing the “Daily Power Production of Solar Panels” Kaggle dataset. Furthermore, an innovative loss function termed DILATE is introduced to train the proposed model specifically for multistep and nonstationary time series forecasting. The outcomes have been subjected to a comparative analysis with alternative algorithms, such as neural basis expansion analysis for interpretable time series (N-BEATS), neural hierarchical interpolation for time series (N-HiTS), and extreme gradient boosting (XGBoost), using several evaluation metrics, including the absolute percentage error (MAE), mean square error (MSE), and root mean square error (RMSE). The model presented in this study exhibited significant performance improvements compared with traditional statistical and machine learning techniques. This is evident from the achieved values of MAE, MSE, and RMSE, which were 1.19, 2.08, and 1.44, respectively. In contrast, the machine learning approach utilizing the Holt–Winters method for time series forecasting in additive mode yielded MAE, MSE, and RMSE scores of 4.126, 29.105, and 5.3949, respectively.
Keywords: PV forecasting; temporal fusion transformer (TFT); LSTM; GRU; N-BEATS; N-HiTS; DILATE; XGBoost PV forecasting; temporal fusion transformer (TFT); LSTM; GRU; N-BEATS; N-HiTS; DILATE; XGBoost

Share and Cite

MDPI and ACS Style

Mazen, F.M.A.; Shaker, Y.; Abul Seoud, R.A. Forecasting of Solar Power Using GRU–Temporal Fusion Transformer Model and DILATE Loss Function. Energies 2023, 16, 8105. https://doi.org/10.3390/en16248105

AMA Style

Mazen FMA, Shaker Y, Abul Seoud RA. Forecasting of Solar Power Using GRU–Temporal Fusion Transformer Model and DILATE Loss Function. Energies. 2023; 16(24):8105. https://doi.org/10.3390/en16248105

Chicago/Turabian Style

Mazen, Fatma Mazen Ali, Yomna Shaker, and Rania Ahmed Abul Seoud. 2023. "Forecasting of Solar Power Using GRU–Temporal Fusion Transformer Model and DILATE Loss Function" Energies 16, no. 24: 8105. https://doi.org/10.3390/en16248105

APA Style

Mazen, F. M. A., Shaker, Y., & Abul Seoud, R. A. (2023). Forecasting of Solar Power Using GRU–Temporal Fusion Transformer Model and DILATE Loss Function. Energies, 16(24), 8105. https://doi.org/10.3390/en16248105

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop