research-article

Multivariate solar power time series forecasting using multilevel data fusion and deep neural networks

Authors:

Sarah Almaghrabi,

Margaret Hamilton,

Mohammad Saiedur RahamanAuthors Info & Claims

Volume 104, Issue C

https://doi.org/10.1016/j.inffus.2023.102180

Published: 12 April 2024 Publication History

Abstract

Accurate forecasting of regional solar photovoltaic power (SPVP) generation is essential for efficient energy management and planning. Existing approaches have shown the effectiveness of decomposing the time series to model the stochastic variability in SPVP data. However, these approaches have limitations in extracting and exploiting both spatial and temporal information from complex and high-dimensional data from multiple sources with intricate relationships, which can impact the accuracy of predictions. In this paper, we propose a novel approach called multilevel data fusion and neural basis expansion analysis (MF-NBEA) for forecasting aggregated regional-level SPVP generation. MF-NBEA integrates exogenous data at multiple levels, uses supervised and unsupervised encoders to provide compact data representation, and enhances model learning from complex data by incorporating spatial information. It also includes a sequence analyser module based on a neural network decomposition mechanism to learn the variability in data and incorporates a residuals learner module to improve overall predictions. We evaluate MF-NBEA using two real-world datasets and find that it outperforms state-of-the-art deep learning methods in terms of forecast accuracy. Furthermore, MF-NBEA facilitates information fusion and knowledge extraction to provide interpretable predictions regarding trend, seasonality, and residual components. The insights gained from our approach inform decision-making for energy management and planning, and can lead to more efficient and sustainable resource utilisation.

Highlights

•

MF-NBEA for multivariate solar power time series forecasting.

•

A 3D autoencoder encodes spatial and temporal information from heterogeneous sources.

•

Interpretable forecasting in terms of trend, seasonality, and residuals.

References

[1]

ARENA, Large-scale solar, 2022, URL https://arena.gov.au/renewable-energy/large-scale-solar/. (Accessed 30 May 2022).

[2]

P. Chen, S. Liu, C. Shi, B. Hooi, B. Wang, X. Cheng, NeuCast: Seasonal Neural Forecast of Power Grid Time Series, in: IJCAI, 2018, pp. 3315–3321.

[3]

Olivares K.G., Challu C., Marcjasz G., Weron R., Dubrawski A., Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx, 2021, arXiv preprint arXiv:2104.05522.

[4]

Mathe J., Miolane N., Sebastien N., Lequeux J., PVNet: A LRCN architecture for spatio-temporal photovoltaic PowerForecasting from numerical weather prediction, 2019, arXiv preprint arXiv:1902.01453.

[5]

He X., Shi S., Geng X., Yu J., Xu L., Multi-step forecasting of multivariate time series using multi-attention collaborative network, Expert Syst. Appl. 211 (2023).

Digital Library

[6]

Liu J., Fang W., Zhang X., Yang C., An improved photovoltaic power forecasting model with the assistance of aerosol index data, IEEE Trans. Sustain. Energy 6 (2) (2015) 434–442.

[7]

Huang C.-J., Kuo P.-H., Multiple-input deep convolutional neural network model for short-term photovoltaic power forecasting, IEEE Access 7 (2019) 74822–74834.

[8]

AlKandari M., Ahmad I., Solar power generation forecasting using ensemble approach based on deep learning and statistical methods, Appl. Comput. Inform. (2020).

[9]

Lin Y., Koprinska I., Rana M., SSDNet: State space decomposition neural network for time series forecasting, in: ICDM, IEEE, 2021, pp. 370–378.

[10]

Almaghrabi S., Rana M., Hamilton M., Rahaman M.S., Solar power time series forecasting utilising wavelet coefficients, Neurocomputing 508 (2022) 182–207.

[11]

Chai S., Xu Z., Jia Y., Wong W.K., A robust spatiotemporal forecasting framework for photovoltaic generation, IEEE Trans. Smart Grid 11 (6) (2020) 5370–5382.

[12]

Rana M., Koprinska I., Forecasting electricity load with advanced wavelet neural networks, Neurocomputing 182 (2016) 118–132.

Digital Library

[13]

Stefenon S.F., Kasburg C., Freire R.Z., Silva Ferreira F.C., Bertol D.W., Nied A., Photovoltaic power forecasting using wavelet Neuro-Fuzzy for active solar trackers, J. Intell. Fuzzy Systems (2021) 1–14. Preprint.

[14]

J. Wang, Z. Wang, J. Li, J. Wu, Multilevel wavelet decomposition network for interpretable time series analysis, in: Proceedings of the 24th ACM SIGKDD, 2018, pp. 2437–2446.

[15]

B.N. Oreshkin, D. Carpov, N. Chapados, Y. Bengio, N-BEATS: Neural basis expansion analysis for interpretable time series forecasting, in: ICLR, 2019.

[16]

Clean Energy Council B.N., large-scale solar, 2022, URL https://www.cleanenergycouncil.org.au/resources/technologies/large-scale-solar. (Accessed 30 May 2022).

[17]

G. Lai, W.-C. Chang, Y. Yang, H. Liu, Modeling long-and short-term temporal patterns with deep neural networks, in: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, 2018, pp. 95–104.

[18]

Shih S.-Y., Sun F.-K., Lee H.-y., Temporal pattern attention for multivariate time series forecasting, Mach. Learn. 108 (2019) 1421–1441.

Digital Library

[19]

Z. Lin, J. Feng, Z. Lu, Y. Li, D. Jin, Deepstn+: Context-aware spatial-temporal neural network for crowd flow prediction in metropolis, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33, No. 01, 2019, pp. 1020–1027.

[20]

R.-G. Cirstea, C. Guo, B. Yang, T. Kieu, X. Dong, S. Pan, Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting, in: 31st International Joint Conference on Artificial Intelligence, IJCAI, 2022, pp. 1994–2001.

[21]

Li Z., Yu J., Zhang G., Xu L., Dynamic spatio-temporal graph network with adaptive propagation mechanism for multivariate time series forecasting, Expert Syst. Appl. 216 (2023).

[22]

Li Z.L., Zhang G.W., Yu J., Xu L.Y., Dynamic graph structure learning for multivariate time series forecasting, Pattern Recognit. 138 (2023).

[23]

Huang W.-C., Chen C.-T., Lee C., Kuo F.-H., Huang S.-H., Attentive gated graph sequence neural network-based time-series information fusion for financial trading, Inf. Fusion 91 (2023) 261–276.

[24]

Z. Shao, Z. Zhang, F. Wang, W. Wei, Y. Xu, Spatial-temporal identity: A simple yet effective baseline for multivariate time series forecasting, in: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022, pp. 4454–4458.

[25]

Karpatne A., Ebert-Uphoff I., Ravela S., Babaie H.A., Kumar V., Machine learning for the geosciences: Challenges and opportunities, IEEE Trans. Knowl. Data Eng. 31 (8) (2018) 1544–1554.

Digital Library

[26]

Markovics D., Mayer M.J., Comparison of machine learning methods for photovoltaic power forecasting based on numerical weather prediction, Renew. Sustain. Energy Rev. 161 (2022).

[27]

Sheng H., Ray B., Shao J., Lasantha D., Das N., Generalization of solar power yield modeling using knowledge transfer, Expert Syst. Appl. 201 (2022).

[28]

Cannizzaro D., Aliberti A., Bottaccioli L., Macii E., Acquaviva A., Patti E., Solar radiation forecasting based on convolutional neural network and ensemble learning, Expert Syst. Appl. 181 (2021).

[29]

Wai R.-J., Lai P.-X., Design of intelligent solar PV power generation forecasting mechanism combined with weather information under lack of real-time power generation data, Energies 15 (10) (2022) 3838.

[30]

Khan Z.A., Hussain T., Haq I.U., Ullah F.U.M., Baik S.W., Towards efficient and effective renewable energy prediction via deep learning, Energy Rep. 8 (2022) 10230–10243.

[31]

Lai C.S., Zhong C., Pan K., Ng W.W., Lai L.L., A deep learning based hybrid method for hourly solar radiation forecasting, Expert Syst. Appl. 177 (2021).

[32]

Bai S., Kolter J.Z., Koltun V., An empirical evaluation of generic convolutional and recurrent networks for sequence modeling, 2018, arXiv preprint arXiv:1803.01271.

[33]

Lin Y., Koprinska I., Rana M., Temporal convolutional neural networks for solar power forecasting, in: 2020 International Joint Conference on Neural Networks, IJCNN, IEEE, 2020, pp. 1–8.

[34]

Perera M., De Hoog J., Bandara K., Halgamuge S., Multi-resolution, multi-horizon distributed solar PV power forecasting with forecast combinations, Expert Syst. Appl. (2022).

[35]

Khan W., Walker S., Zeiler W., Improved solar photovoltaic energy generation forecast using deep learning-based ensemble stacking approach, Energy 240 (2022).

[36]

M. Rana, A. Rahman, J. Jin, A Data-driven Approach for Forecasting State Level Aggregated Solar Photovoltaic Power Production, in: IJCNN, 2020, pp. 1–8.

[37]

Almaghrabi S., Rana M., Hamilton M., Rahaman M.S., Spatially aggregated photovoltaic power prediction using wavelet and convolutional neural networks, in: IJCNN, IEEE, 2021, pp. 1–8.

[38]

Zhang Y., Beaudin M., Taheri R., Zareipour H., Wood D., Day-ahead power output forecasting for small-scale solar photovoltaic electricity generators, IEEE Trans. Smart Grid 6 (5) (2015) 2253–2262.

[39]

Li Y., Zhu Z., Kong D., Han H., Zhao Y., EA-LSTM: Evolutionary attention-based LSTM for time series prediction, Knowl.-Based Syst. 181 (2019).

Digital Library

[40]

Liu R., Chen L., Hu W., Huang Q., Short-term load forecasting based on LSTNet in power system, Int. Trans. Electr. Energy Syst. 31 (12) (2021).

[41]

Shi X., Chen Z., Wang H., Yeung D.-Y., Wong W.-K., Woo W.-c., Convolutional LSTM network: A machine learning approach for precipitation nowcasting, Adv. Neural Inf. Process. Syst. 28 (2015).

[42]

Z. Wu, S. Pan, G. Long, J. Jiang, X. Chang, C. Zhang, Connecting the dots: Multivariate time series forecasting with graph neural networks, in: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020, pp. 753–763.

[43]

Khodayar M., Mohammadi S., Khodayar M.E., Wang J., Liu G., Convolutional graph autoencoder: A generative deep neural network for probabilistic spatio-temporal solar irradiance forecasting, IEEE Trans. Sustain. Energy 11 (2) (2019) 571–583.

[44]

Simeunović J., Schubnel B., Alet P.-J., Carrillo R.E., Spatio-temporal graph neural networks for multi-site PV power forecasting, IEEE Trans. Sustain. Energy 13 (2) (2021) 1210–1220.

[45]

Melgar-García L., Gutiérrez-Avilés D., Rubio-Escudero C., Troncoso A., A novel distributed forecasting method based on information fusion and incremental learning for streaming time series, Inf. Fusion 95 (2023) 163–173.

[46]

Ramírez-Gallego S., Fernández A., García S., Chen M., Herrera F., Big data: Tutorial and guidelines on information and process fusion for analytics algorithms with MapReduce, Inf. Fusion 42 (2018) 51–61.

[47]

Castán-Lascorz M., Jiménez-Herrera P., Troncoso A., Asencio-Cortés G., A new hybrid method for predicting univariate and multivariate time series based on pattern forecasting, Inform. Sci. 586 (2022) 611–627.

[48]

Abushaqra F.M., Xue H., Ren Y., Salim F.D., PIETS: Parallelised irregularity encoders for forecasting with heterogeneous time-series, in: ICDM, IEEE, 2021, pp. 976–981.

[49]

Di Piazza A., Di Piazza M.C., La Tona G., Luna M., An artificial neural network-based forecasting model of energy-related time series for electrical grid management, Math. Comput. Simulation 184 (2021) 294–305.

[50]

Castangia M., Aliberti A., Bottaccioli L., Macii E., Patti E., A compound of feature selection techniques to improve solar radiation forecasting, Expert Syst. Appl. 178 (2021).

[51]

Liu T., Wei H., Zhang C., Zhang K., Time series forecasting based on wavelet decomposition and feature extraction, Neural Comput. Appl. 28 (1) (2017) 183–195.

[52]

Rai A., Shrivastava A., Jana K.C., A CNN-BiLSTM based deep learning model for mid-term solar radiation prediction, Int. Trans. Electr. Energy Syst. 31 (9) (2021).

[53]

Zhang S., Chen Y., Zhang W., Feng R., A novel ensemble deep learning model with dynamic error correction and multi-objective ensemble pruning for time series forecasting, Inform. Sci. 544 (2021) 427–445.

[54]

González Ordiano J.Á., Waczowicz S., Hagenmeyer V., Mikut R., Energy forecasting tools and services, Wiley Interdiscip. Rev. Data Min. Knowl. Discov. 8 (2) (2018).

[55]

Yang Z., Mourshed M., Liu K., Xu X., Feng S., A novel competitive swarm optimized RBF neural network model for short-term solar power generation forecasting, Neurocomputing 397 (2020) 415–421.

[56]

Makridakis S., Hibon M., ARMA models and the Box–Jenkins methodology, J. Forecast. 16 (3) (1997) 147–163.

[57]

Salinas D., Flunkert V., Gasthaus J., Januschowski T., DeepAR: Probabilistic forecasting with autoregressive recurrent networks, Int. J. Forecast. 36 (3) (2020) 1181–1191.

[58]

C. Fan, Y. Zhang, Y. Pan, X. Li, C. Zhang, R. Yuan, D. Wu, W. Wang, J. Pei, H. Huang, Multi-horizon time series forecasting with temporal attention learning, in: Proceedings of the 25th ACM SIGKDD, 2019, pp. 2527–2535.

[59]

F. Zhou, L. Li, K. Zhang, G. Trajcevski, F. Yao, Y. Huang, T. Zhong, J. Wang, Q. Liu, Forecasting the evolution of hydropower generation, in: Proceedings of the 26th ACM SIGKDD, 2020, pp. 2861–2870.

[60]

Theodosiou M., Forecasting monthly and quarterly time series using STL decomposition, Int. J. Forecast. 27 (4) (2011) 1178–1195.

[61]

Du Z., Qin M., Zhang F., Liu R., Multistep-ahead forecasting of chlorophyll a using a wavelet nonlinear autoregressive network, Knowl.-Based Syst. 160 (2018) 61–70.

[62]

Zhang Z., Hong W.-C., Application of variational mode decomposition and chaotic grey wolf optimizer with support vector regression for forecasting electric loads, Knowl.-Based Syst. 228 (2021).

Digital Library

[63]

Qiu X., Suganthan P.N., Amaratunga G.A., Ensemble incremental learning random vector functional link network for short-term electric load forecasting, Knowl.-Based Syst. 145 (2018) 182–196.

Digital Library

[64]

Yuan F., Che J., An ensemble multi-step M-RMLSSVR model based on VMD and two-group strategy for day-ahead short-term load forecasting, Knowl.-Based Syst. 252 (2022).

[65]

Shakya A., Michael S., Saunders C., Armstrong D., Pandey P., Chalise S., Tonkoski R., Solar irradiance forecasting in remote microgrids using markov switching model, IEEE Trans. Sustain. Energy 8 (3) (2016) 895–905.

[66]

Lan H., Zhang C., Hong Y.-Y., He Y., Wen S., Day-ahead spatiotemporal solar irradiation forecasting using frequency-based hybrid principal component analysis and neural network, Appl. Energy 247 (2019) 389–402.

[67]

Mandal P., Madhira S.T.S., Meng J., Pineda R.L., et al., Forecasting power output of solar photovoltaic system using wavelet transform and artificial intelligence techniques, Procedia Comput. Sci. 12 (2012) 332–337.

[68]

Sibtain M., Li X., Saleem S., Asad M.S., Tahir T., Apaydin H., et al., A multistage hybrid model ICEEMDAN-SE-VMD-RDPG for a multivariate solar irradiance forecasting, IEEE Access 9 (2021) 37334–37363.

[69]

Xie T., Zhang G., Liu H., Liu F., Du P., A hybrid forecasting method for solar output power based on variational mode decomposition, deep belief networks and auto-regressive moving average, Appl. Sci. 8 (10) (2018) 1901.

[70]

Press W.H., Teukolsky S.A., Vetterling W.T., Flannery B.P., Numerical Recipes 3rd Edition: The Art of Scientific Computing, Cambridge University Press, 2007.

[71]

K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770–778.

[72]

O’Shea K., Nash R., An introduction to convolutional neural networks, 2015, arXiv preprint arXiv:1511.08458.

[73]

Atiya A.F., Why does forecast combination work so well?, Int. J. Forecast. 36 (1) (2020) 197–200.

[74]

S. Kobayashi, J. von Oswald, B. Grewe, On the reversed bias-variance tradeoff in deep ensembles, in: ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning, 2021.

[75]

Antonanzas J., Osorio N., Escobar R., Urraca R., Martinez-de Pison F.J., Antonanzas-Torres F., Review of photovoltaic power forecasting, Sol. Energy 136 (2016) 78–111.

[76]

Almaghrabi S., Rana M., Hamilton M., Rahaman M.S., Forecasting regional level solar power generation using advanced deep learning approach, in: IJCNN, IEEE, 2021, pp. 1–7.

[77]

Challu C., Olivares K.G., Oreshkin B.N., Ramirez F.G., Canseco M.M., Dubrawski A., NHITS: Neural hierarchical interpolation for time series forecasting, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, No. 6, 2023, pp. 6989–6997.

[78]

Deng J., Deng J., Yin D., Jiang R., Song X., TTS-norm: Forecasting tensor time series via multi-way normalization, ACM Trans. Knowl. Discov. Data (2023).

[79]

J. Choi, H. Choi, J. Hwang, N. Park, Graph neural controlled differential equations for traffic forecasting, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, No. 6, 2022, pp. 6367–6374.

[80]

Kuhn M., Johnson K., Applied Predictive Modeling, Springer, 2013, pp. 4–5.

[81]

Arrieta A.B., Díaz-Rodríguez N., Del Ser J., Bennetot A., Tabik S., Barbado A., García S., Gil-López S., Molina D., Benjamins R., et al., Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI, Inf. Fusion 58 (2020) 82–115.

Digital Library

Cited By

Souto H(2024)Charting new avenues in financial forecasting with TimesNetExpert Systems with Applications: An International Journal10.1016/j.eswa.2024.124851255:PDOnline publication date: 21-Nov-2024
https://dl.acm.org/doi/10.1016/j.eswa.2024.124851

Recommendations

Numerical Weather Prediction Data Free Solar Power Forecasting with Neural Networks
e-Energy '18: Proceedings of the Ninth International Conference on Future Energy Systems

The worldwide increase in renewable energy penetration levels has made accuracy, availability, and affordability of wind and solar energy forecasting systems an integral part of the modern power grids. The present paper describes an approach to ...
Spatio-temporal heterogeneous graph using multivariate earth observation time series: Application for drought forecasting
Abstract
Accurate forecasting is required for the effective risk management of drought disasters. Many machine learning- and deep learning-based models have been proposed for drought forecasting, however, they cannot handle the temporal and/or ...
Highlights
- A novel HetSPGraph approach with three layers is proposed for drought forecasting.
Short term wind power forecasting using time series neural networks
EAIA '11: Proceedings of the 2011 Emerging M&S Applications in Industry and Academia Symposium

Forecasting wind power energy is very important issue in a liberalized market and the prediction tools can make wind energy be competitive in these kinds of markets. This paper will study an application of time-series and neural network for predicting ...

Comments

Information & Contributors

Information

Published In

cover image Information Fusion

Information Fusion Volume 104, Issue C

Apr 2024

751 pages

Issue’s Table of Contents

The Author(s).

Publisher

Elsevier Science Publishers B. V.

Netherlands

Publication History

Published: 12 April 2024

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 25 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Souto H(2024)Charting new avenues in financial forecasting with TimesNetExpert Systems with Applications: An International Journal10.1016/j.eswa.2024.124851255:PDOnline publication date: 21-Nov-2024
https://dl.acm.org/doi/10.1016/j.eswa.2024.124851

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents