Short-Term Multivariate Rooftop PV Power Forecasting using a Patching-Based Transformer Model: A Case Study

Quynh Thi Thanh Nguyen, Huy Quang Giap, Ky Trung Nguyen, Tan Van Nguyen

Abstract


Rooftop solar energy constitutes a crucial component in the operation of smart grids, wherein the electrical system is managed in a decentralized and optimized approach. This energy source is characterized by its cleanliness, abundance, and cost-free nature; however, effective utilization of this resource necessitates accurate forecasting. Prior research has indicated that univariate solar energy forecasting yields superior outcomes in comparison to multivariate forecasting methodologies. Nevertheless, the accuracy of forecasting diminishes significantly in instances of the unavailability of historical target data. In the present study, we introduce a novel approach for multivariate solar energy forecasting. This approach is predicated on the transformer model and it integrates mechanisms such as patching and channel independence to attain elevated accuracy while minimizing time and computational resource requirements, ensuring compatibility with smart meters. The efficacy of the method is demonstrated through a real-world case study conducted in Central Vietnam, revealing an enhancement of at least 6.9% in Mean Absolute Error (MAE) relative to traditional transformer models, the DLinear model, and the TSmixer model.

Keywords


PV power forecasting, PATCHTST; short-term multivariate solar forecasting

Full Text:

PDF

References


S. Matemilola, O. Fadeyi and T. Sijuade, “Paris agreement,” Encyclopedia of sustainable management, vol. 2020, p. 1, 2020.

“Photovoltaic Geographical Information System (PVGIS) re.jrc.ec.europa.eu,” [Online]. Available: re.jrc.ec.europa.eu. [Accessed 10 08 2024].

“Solar (photovoltaic) panel prices ourworldindata.org,” [Online]. Available: ourworldindata.org. [Accessed 10 08 2024].

A. E. L. Rivas and T. Abrao, “Faults in smart grid systems: Monitoring, detection and classification,” Electric Power Systems Research, vol. 189, p. 106602, 2020.

G. Xiu-Yan, L. Jie-Mei, Y. Yuan and T. He-Ping, “Global horizontal irradiance prediction model considering the effect of aerosol optical depth based on the Informer model,” Renewable Energy, vol. 220, p. 119671, 2024.

X. Zhao, H. Wei, H. Wang, T. Zhu and K. Zhang, “3D-CNN-based feature extraction of ground-based cloud images for direct normal irradiance prediction,” Solar Energy, vol. 181, pp. 510-518, 2019.

G. Bae, “Real-Time DNI and DHI Prediction Using Weather Information via LGBM,” chez Science and Information Conference, 2023.

R. Gallo, M. Castangia, A. Macii, E. Macii, E. Patti and A. Aliberti, “Solar radiation forecasting with deep learning techniques integrating geostationary satellite images,” Engineering Applications of Artificial Intelligence, vol. 116, p. 105493, 2022.

D. S. Kumar, G. M. Yagli, M. Kashyap and D. Srinivasan, “Solar irradiance resource and forecasting: a comprehensive review,” IET Renewable Power Generation, vol. 14, pp. 1641-1656, 2020.

X. Xiang, X. Li, Y. Zhang and J. Hu, “A short-term forecasting method for photovoltaic power generation based on the TCN-ECANet-GRU hybrid model,” Scientific Reports, vol. 14, p. 6744, 2024.

P. Singla, M. Duhan and S. Saroha, “A comprehensive review and analysis of solar forecasting techniques,” Frontiers in Energy, pp. 1-37, 2021.

R. Ahmed, V. Sreeram, Y. Mishra and M. D. Arif, “A review and evaluation of the state-of-the-art in PV solar power forecasting: Techniques and optimization,” Renewable and Sustainable Energy Reviews, vol. 124, p. 109792, 2020.

G. Terrén-Serrano and M. Mart??nez-Ramón, “Deep learning for intra-hour solar forecasting with fusion of features extracted from infrared sky images,” Information Fusion, vol. 95, pp. 42-61, 2023.

T. Cabello-López, M. Carranza-Garc??a, J. C. Riquelme and J. Garc??a-Gutiérrez, “Forecasting solar energy production in Spain: A comparison of univariate and multivariate models at the national level,” Applied Energy, vol. 350, p. 121645, 2023.

H. Verbois, R. Huva, A. Rusydi and W. Walsh, “Solar irradiance forecasting in the tropics using numerical weather prediction and statistical learning,” Solar Energy, vol. 162, pp. 265-277, 2018.

T. R. Ayodele, A. S. O. Ogunjuyigbe, A. Amedu and J. L. Munda, “Prediction of global solar irradiation using hybridized k-means and support vector regression algorithms,” Renewable Energy Focus, vol. 29, pp. 78-93, 2019.

O. Henni and M. Belarbi, “Effect of mathematical models on forecasting analysis of photovoltaic power,” chez 2021 9th International Conference on Smart Grid (icSmartGrid), 2021.

R. Al-Hajj, A. Assi and M. M. Fouad, “Stacking-Based Ensemble of Support Vector Regressors for One-Day Ahead Solar Irradiance Prediction,” chez 2019 8th International Conference on Renewable Energy Research and Applications (ICRERA), 2019.

R. Al-Hajj, A. Assi and M. M. Fouad, “Multi-level Stacking of Long Short Term Memory Recurrent Models for Time Series Forecasting of Solar Radiation,” chez 2021 10th International Conference on Renewable Energy Research and Application (ICRERA), 2021.

K. Yahya, S. Al-mayyahi, M. Aldababsa, A. E. Yahya and R. D. Sarreb, “Machine Learning Techniques for Solar Power Output Predicting,” International Journal of Smart Grid-ijSmartGrid, vol. 8, n° %12, pp. 98--107, 2024.

H. Raju and S. Das, “CNN-based deep learning model for solar wind forecasting,” Solar Physics, vol. 296, p. 134, 2021.

T. Nguyen, V. Debusschere, C. Bobineau and R. Rigo-Mariani, “Comparing high accurate regression models for short-term load forecasting in smart buildings,” chez IECON 2020 The 46th annual conference of the IEEE industrial electronics society, 2020.

M. Jaihuni, J. K. Basak, F. Khan, F. G. Okyere, T. Sihalath, A. Bhujel, J. Park, D. H. Lee and H. T. Kim, “A novel recurrent neural network approach in forecasting short term solar irradiance,” ISA transactions, vol. 121, pp. 63-74, 2022.

S. X. Chen, H. B. Gooi and M. Q. Wang, “Solar radiation forecast based on fuzzy logic and neural networks,” Renewable energy, vol. 60, pp. 195-201, 2013.

X. Huang, J. Shi, B. Gao, Y. Tai, Z. Chen and J. Zhang, “Forecasting hourly solar irradiance using hybrid wavelet transformation and Elman model in smart grid,” IEEE access, vol. 7, pp. 139909-139923, 2019.

A. Yildirim, M. Bilgili and A. Ozbek, “One-hour-ahead solar radiation forecasting by MLP, LSTM, and ANFIS approaches,” Meteorology and Atmospheric Physics, vol. 135, p. 10, 2023.

B. Gao, X. Huang, J. Shi, Y. Tai and J. Zhang, “Hourly forecasting of solar irradiance based on CEEMDAN and multi-strategy CNN-LSTM neural networks,” Renewable Energy, vol. 162, pp. 1665-1683, 2020.

N. Dong, J.-F. Chang, A.-G. Wu and Z.-K. Gao, “A novel convolutional neural network framework based solar irradiance prediction method,” International Journal of Electrical Power & Energy Systems, vol. 114, p. 105411, 2020.

N. Sharma, V. Puri, S. Mahajan, L. Abualigah, R. A. Zitar and A. H. Gandomi, “Solar power forecasting beneath diverse weather conditions using GD and LM-artificial neural networks,” Scientific reports, vol. 13, p. 8517, 2023.

S. Shamshirband, K. Mohammadi, H. Khorasanizadeh, L. Yee, M. Lee, D. Petkovi? and E. Zalnezhad, “Estimating the diffuse solar radiation using a coupled support vector machine--wavelet transform model,” Renewable and Sustainable Energy Reviews, vol. 56, pp. 428-435, 2016.

E. Y. M. &. T. O. Irmak, “Enhanced PV Power Prediction Considering PM10 Parameter by Hybrid JAYA-ANN Model,” Electric Power Components and Systems, vol. 52, n° %111, p. 1998–2007, 2024.

K. S. Kalyan, A. Rajasekharan and S. Sangeetha, “Ammus: A survey of transformer-based pretrained models in natural language processing,” arXiv preprint arXiv:2108.05542, 2021.

J. Bi, Z. Zhu and Q. Meng, “Transformer in computer vision,” chez 2021 IEEE International conference on computer science, electronic information engineering and intelligent control technology (CEI), 2021.

Y. Wang, A. Mohamed, D. Le, C. Liu, A. Xiao, J. Mahadeokar, H. Huang, A. Tjandra, X. Zhang, F. Zhang, C. Fuegen, G. Zweig, M. L. Seltzer, “Transformer-based acoustic modeling for hybrid speech recognition,” chez ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020.

S. Ahmed, I. E. Nielsen, A. Tripathi, S. Siddiqui, R. P. Ramachandran and G. Rasool, “Transformers in time-series analysis: A tutorial,” Circuits, Systems, and Signal Processing, vol. 42, pp. 7433-7466, 2023.

H. Zhou, S. Zhang, J. Peng, S. Zhang, J. Li, H. Xiong and W. Zhang, “Informer: Beyond efficient transformer for long sequence time-series forecasting,” chez Proceedings of the AAAI conference on artificial intelligence, 2021.

H. Wu, J. Xu, J. Wang and M. Long, “Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting,” Advances in neural information processing systems, vol. 34, pp. 22419-22430, 2021.

T. Zhou, Z. Ma, Q. Wen, X. Wang, L. Sun and R. Jin, “Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting,” chez International conference on machine learning, 2022.

V. Ekambaram, A. Jati, N. Nguyen, P. Sinthong and J. Kalagnanam, “Tsmixer: Lightweight MLP-mixer model for multivariate time series forecasting,” chez Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023.

Y. Nie, N. H. Nguyen, P. Sinthong and J. Kalagnanam, “A time series is worth 64 words: Long-term forecasting with transformers,” arXiv preprint arXiv:2211.14730, 2022.

A. Zeng, M. Chen, L. Zhang and Q. Xu, “Are transformers effective for time series forecasting?,” chez Proceedings of the AAAI conference on artificial intelligence, 2023.




DOI (PDF): https://doi.org/10.20508/ijrer.v15i4.15779.g9130

Refbacks

  • There are currently no refbacks.


Online ISSN: 1309-0127

Publisher: Gazi University

IJRER is indexed in EI Compendex, SCOPUS, EBSCO, WEB of SCIENCE (Clarivate Analytics)and CrossRef.

IJRER has been indexed in Emerging Sources Citation Index from 2016 in web of science.

WEB of SCIENCE in 2025; 

h=35,

Average citation per item=6.59

Last three Years Impact Factor=(1947+1753+1586)/(146+201+78)=5286/425=12.43

Category Quartile:Q4