Photovoltaic Energy Production Forecasting through Machine Learning Methods: A Scottish Solar Farm Case Study
Abstract
:1. Introduction
2. Materials and Methods
2.1. Dataset
2.2. Data Analysis
2.3. Methodology
2.3.1. Linear Regression
2.3.2. k-Nearest Neighbours
2.3.3. Decision Tree
2.3.4. eXtreme Gradient Boosting
2.3.5. Light Gradient Boosting
2.3.6. Multi-Layer Perceptron
2.3.7. Elman Neural Network
2.3.8. Long Short-Term Memory
2.3.9. Metrics
2.3.10. Pre-processing
3. Results
4. Conclusions and Future Work
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
Abbreviations
DT | Decision Tree |
ENN | Elman Neural Network |
kNN | k-Nearest Neighbour |
LGBM | Light Gradient Boosting Machine |
LR | Linear Regression |
LSTM | Long Short-Term Memory |
MAE | Mean Absolute Error |
MLP | Multi-Layer Perceptron |
PV | Photovoltaic |
RMSE | Root Mean Square Error |
XGB | eXtreme Gradient Boost |
References
- Dhabi, A. Irena. Renewable Energy Statistics. 2020. Available online: http://www.evwind.es/2020/06/05/renewable-energy-costs-plummet-according-toirena/75021 (accessed on 3 September 2021).
- Nassar, N.T.; Wilburn, D.R.; Goonan, T.G. Byproduct metal requirements for U.S. Wind and solar photovoltaic electricity generation up to the year 2040 under various clean power plan scenarios. Appl. Energy 2016, 183, 1209–1226. [Google Scholar] [CrossRef]
- Zhang, Y.J.; Ideue, T.; Onga, M.; Qin, F.; Suzuki, R.; Zak, A.; Tenne, R.; Smet, J.H.; Iwasa, Y. Enhanced intrinsic photovoltaic effect in tungsten disulfide nanotubes. Nature 2019, 570, 349–353. [Google Scholar] [CrossRef]
- Buwei, W.; Jianfeng, C.; Bo, W.; Shuanglei, F. A Solar Power Prediction Using Support Vector Machines Based on Multi-Source Data Fusion. In Proceedings of the 2018 International Conference on Power System Technology (POWERCON), Guangzhou, China, 6–8 November 2018; pp. 4573–4577. [Google Scholar]
- Fritts, C.E. On a new form of selenium photocell. Am. J. Sci. 1883, 26, 465–472. Available online: http://www.pveducation.org/node/310 (accessed on 3 September 2021). [CrossRef]
- Geisz, J.F.; France, R.M.; Schulte, K.L.; Steiner, M.A.; Norman, A.G.; Guthrey, H.L.; Young, M.R.; Song, T.; Moriarty, T. Six-junction iii–v solar cells with 47.1% conversion efficiency under 143 suns concentration. Nat. Energy 2020, 5, 326–335. [Google Scholar] [CrossRef]
- Fernandez-Jimenez, L.A.; Muñoz-Jimenez, A.; Falces, A.; Mendoza-Villena, M.; Garcia-Garrido, E.; Lara-Santillan, P.M.; Zorzano-Alba, E.; Zorzano-Santamaria, P.J. Short-term power forecasting system for photovoltaic plants. Renew. Energy 2012, 44, 311–317. [Google Scholar] [CrossRef]
- Monteiro, C.; Santos, T.; Fernandez-Jimenez, L.A.; Ramirez-Rosado, I.J.; Terreros-Olarte, M.S. Short-term power forecasting model for photovoltaic plants based on historical similarity. Energies 2013, 6, 2624–2643. [Google Scholar] [CrossRef]
- Lorenz, E.; Heinemann, D.; Kurz, C. Local and regional photovoltaic power prediction for large scale grid integration: Assessment of a new algorithm for snow detection. Prog. Photovolt. Res. Appl. 2012, 20, 760–769. [Google Scholar] [CrossRef]
- Bourdeau, M.; Zhai, X.Q.; Nefzaoui, E.; Guo, X.; Chatellier, P. Modeling and forecasting building energy consumption: A review of data-driven techniques. Sustain. Cities Soc. 2019, 48, 101533. [Google Scholar] [CrossRef]
- Almeida, M.P.; Perpiñán, O.; Narvarte, L. Pv power forecast using a nonparametric pv model. Sol. Energy 2015, 115, 354–368. [Google Scholar] [CrossRef] [Green Version]
- Mellit, A.; Massi Pavan, A.; Lughi, V. Short-term forecasting of power production in a large-scale photovoltaic plant. Sol. Energy 2014, 105, 401–413. [Google Scholar] [CrossRef]
- Shi, J.; Lee, W.J.; Liu, Y.; Yang, Y.; Wang, P. Forecasting power output of photovoltaic systems based on weather classification and support vector machines. IEEE Trans. Ind. Appl. 2012, 48, 1064–1069. [Google Scholar] [CrossRef]
- Chen, C.; Duan, S.; Cai, T.; Liu, B. Online 24-h solar power forecasting based on weather type classification using artificial neural network. Sol. Energy 2011, 85, 2856–2870. [Google Scholar] [CrossRef]
- Bouzerdoum, M.; Mellit, A.; Massi Pavan, A. A hybrid model (sarima–svm) for short-term power forecasting of a small-scale grid-connected photovoltaic plant. Sol. Energy 2013, 98, 226–235. [Google Scholar] [CrossRef]
- Muneer, T.; Gago, E.J.; Berrizbeitia, S.E. The Coming of Age of Solar and Wind Power; Springer Nature: Berlin/Heidelberg, Germany, 2022. [Google Scholar] [CrossRef]
- Muneer, T.; Dowell, R. Potential for renewable energy–assisted harvesting of potatoes in scotland. Int. J. Low-Carbon Technol. 2022, 17, 469–481. [Google Scholar] [CrossRef]
- Ruiz, L.G.B.; Rueda, R.; Cuéllar, M.P.; Pegalajar, M.C. Energy consumption forecasting based on elman neural networks with evolutive optimization. Expert Syst. Appl. 2018, 92, 380–389. [Google Scholar] [CrossRef]
- Ruiz, L.G.B.; Cuellar, M.P.; Delgado, M.; Pegalajar, M.C. An application of non-linear autoregressive neural networks to predict energy consumption in public buildings. Energies 2016, 9, 684. [Google Scholar] [CrossRef] [Green Version]
- Ruiz, L.G.B.; Capel, M.I.; Pegalajar, M.C. Parallel memetic algorithm for training recurrent neural networks for the energy efficiency problem. Appl. Soft Comput. 2019, 76, 356–368. [Google Scholar] [CrossRef]
- Saber, A.Y.; Alam, A.K.M.R. Short Term Load Forecasting Using Multiple Linear Regression for Big Data. In Proceedings of the 2017 IEEE Symposium Series on Computational Intelligence (SSCI), Honolulu, HI, USA, 27 November–1 December 2017; pp. 1–6. [Google Scholar]
- Himeur, Y.; Alsalemi, A.; Bensaali, F.; Amira, A. Smart power consumption abnormality detection in buildings using micromoments and improved k-nearest neighbors. Int. J. Intell. Syst. 2021, 36, 2865–2894. [Google Scholar] [CrossRef]
- Mikučionienė, R.; Martinaitis, V.; Keras, E. Evaluation of energy efficiency measures sustainability by decision tree method. Energy Build. 2014, 76, 64–71. [Google Scholar] [CrossRef]
- Galicia, A.; Talavera-Llames, R.; Troncoso, A.; Koprinska, I.; Martínez-Álvarez, F. Multi-step forecasting for big data time series based on ensemble learning. Knowl.-Based Syst. 2019, 163, 830–841. [Google Scholar] [CrossRef]
- Duque-Pintor, F.; Fernández-Gómez, M.; Troncoso, A.; Martínez-Álvarez, F. A new methodology based on imbalanced classification for predicting outliers in electricity demand time series. Energies 2016, 9, 752. [Google Scholar] [CrossRef] [Green Version]
- Yucong, W.; Bo, W. Research on ea-xgboost hybrid model for building energy prediction. J. Phys. Conf. Ser. 2020, 1518, 012082. [Google Scholar] [CrossRef]
- Chowdhury, S.R.; Mishra, S.; Miranda, A.O.; Mallick, P.K. Energy Consumption Prediction Using Light Gradient Boosting Machine Model; Springer Nature Singapore: Singapore, 2021; pp. 413–422. [Google Scholar]
- Iruela, J.R.S.; Ruiz, L.G.B.; Capel, M.I.; Pegalajar, M.C. A tensorflow approach to data analysis for time series forecasting in the energy-efficiency realm. Energies 2021, 14, 4038. [Google Scholar] [CrossRef]
- Soofastaei, A.; Aminossadati, S.M.; Arefi, M.M.; Kizil, M.S. Development of a multi-layer perceptron artificial neural network model to determine haul trucks energy consumption. Int. J. Min. Sci. Technol. 2016, 26, 285–293. [Google Scholar] [CrossRef]
- Dudek, G. Multilayer perceptron for gefcom 2014 probabilistic electricity price forecasting. Int. J. Forecast. 2016, 32, 1057–1060. [Google Scholar] [CrossRef]
- Torres, J.F.; Hadjout, D.; Sebaa, A.; Martínez-Álvarez, F.; Troncoso, A. Deep learning for time series forecasting: A survey. Big Data 2020, 9, 3–21. [Google Scholar] [CrossRef] [PubMed]
- Chai, T.; Draxler, R.R. Root mean square error (rmse) or mean absolute error (mae)?—Arguments against avoiding rmse in the literature. Geosci. Model Dev. 2014, 7, 1247–1250. [Google Scholar] [CrossRef] [Green Version]
- Di Bucchianico, A. Coefficient of Determination (r2). In Encyclopedia of Statistics in Quality and Reliability; Wiley: Hoboken, NJ, USA, 2007. [Google Scholar] [CrossRef]
Date | PV Production |
---|---|
26 May 2015 12:00:00 | 42.8 kWh |
7 May 2017 13:00:00 | 42.3 kWh |
10 June 2015 13:00:00 | 42.2 kWh |
9 May 2013 12:00:00 | 42.0 kWh |
Variable | Relevance |
---|---|
t − 1 | 0.860 |
Hour | 0.065 |
t − 2 | 0.025 |
t − 3 | 0.022 |
Month | 0.016 |
Day | 0.015 |
Year | 0.007 |
Model | P1 | P2 | MAE | RMSE | R2 |
---|---|---|---|---|---|
LR | 0 | 1.00 | 0.04600 | 0.07900 | 0.83800 |
0 | 0.95 | 0.04600 | 0.07900 | 0.83800 | |
0 | 0.90 | 0.04600 | 0.07900 | 0.83800 | |
0 | 0.85 | 0.04600 | 0.07900 | 0.83800 | |
kNN | 16 | 1 | 0.03338 | 0.07053 | 0.87680 |
17 | 1 | 0.03394 | 0.07055 | 0.87680 | |
18 | 1 | 0.03401 | 0.07058 | 0.87670 | |
20 | 1 | 0.03408 | 0.07057 | 0.87670 | |
22 | 1 | 0.03414 | 0.07056 | 0.87670 | |
DT | 16 | 32 | 0.03367 | 0.07034 | 0.87750 |
8 | 32 | 0.03367 | 0.07034 | 0.87750 | |
4 | 32 | 0.03367 | 0.07034 | 0.87750 | |
32 | 16 | 0.03367 | 0.07034 | 0.87750 | |
8 | 16 | 0.03367 | 0.07034 | 0.87750 | |
LGBM | 30 | 800 | 0.03089 | 0.06433 | 0.89750 |
40 | 600 | 0.03090 | 0.06432 | 0.89760 | |
20 | 100 | 0.03103 | 0.06432 | 0.89760 | |
20 | 800 | 0.03119 | 0.06433 | 0.89750 | |
20 | 800 | 0.03125 | 0.06434 | 0.89750 | |
XGB | 900 | 6 | 0.03070 | 0.06420 | 0.89800 |
700 | 6 | 0.03070 | 0.06423 | 0.89780 | |
700 | 7 | 0.03074 | 0.06421 | 0.89790 | |
1000 | 6 | 0.03078 | 0.06427 | 0.89770 | |
900 | 6 | 0.03089 | 0.06420 | 0.89800 | |
MLP | 60 | 80 | 0.03600 | 0.07173 | 0.87260 |
70 | 80 | 0.03620 | 0.07158 | 0.87320 | |
50 | 60 | 0.03672 | 0.07166 | 0.87290 | |
70 | 80 | 0.03718 | 0.07160 | 0.87310 | |
30 | 60 | 0.03843 | 0.07085 | 0.87570 | |
ENN | 300 | 300 | 0.03400 | 0.07064 | 0.87000 |
100 | 100 | 0.03500 | 0.07148 | 0.87000 | |
500 | - | 0.03800 | 0.07319 | 0.86000 | |
100 | - | 0.04055 | 0.07541 | 0.85000 | |
50 | - | 0.04057 | 0.07678 | 0.85000 | |
LSTM | 300 | 300 | 0.04048 | 0.07853 | 0.85000 |
100 | 100 | 0.04065 | 0.07875 | 0.85000 | |
500 | - | 0.04194 | 0.08044 | 0.84000 | |
100 | - | 0.04384 | 0.08056 | 0.84000 | |
50 | - | 0.04401 | 0.08079 | 0.84000 |
Model | MAE | RMSE | R2 |
---|---|---|---|
XGB | 0.0306 | 0.0628 | 0.8945 |
LGBM | 0.0308 | 0.0629 | 0.8941 |
DT | 0.0335 | 0.0689 | 0.8731 |
kNN | 0.0343 | 0.0697 | 0.8701 |
LSTM | 0.0359 | 0.0717 | 0.8623 |
ENN | 0.0363 | 0.0709 | 0.8656 |
MLP | 0.0385 | 0.0704 | 0.8672 |
LR | 0.0459 | 0.0782 | 0.8362 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Cabezón, L.; Ruiz, L.G.B.; Criado-Ramón, D.; J. Gago, E.; Pegalajar, M.C. Photovoltaic Energy Production Forecasting through Machine Learning Methods: A Scottish Solar Farm Case Study. Energies 2022, 15, 8732. https://doi.org/10.3390/en15228732
Cabezón L, Ruiz LGB, Criado-Ramón D, J. Gago E, Pegalajar MC. Photovoltaic Energy Production Forecasting through Machine Learning Methods: A Scottish Solar Farm Case Study. Energies. 2022; 15(22):8732. https://doi.org/10.3390/en15228732
Chicago/Turabian StyleCabezón, L., L. G. B. Ruiz, D. Criado-Ramón, E. J. Gago, and M. C. Pegalajar. 2022. "Photovoltaic Energy Production Forecasting through Machine Learning Methods: A Scottish Solar Farm Case Study" Energies 15, no. 22: 8732. https://doi.org/10.3390/en15228732