Advanced Methods for Photovoltaic Output Power Forecasting: A Review
Source abstract
Abstract
Forecasting is a crucial task for successfully integrating photovoltaic (PV) output power into the grid. The design of accurate photovoltaic output forecasters remains a challenging issue, particularly for multistep-ahead prediction. Accurate PV output power forecasting is critical in a number of applications, such as micro-grids (MGs), energy optimization and management, PV integrated in smart buildings, and electrical vehicle chartering. Over the last decade, a vast literature has been produced on this topic, investigating numerical and probabilistic methods, physical models, and artificial intelligence (AI) techniques. This paper aims at providing a complete and critical review on the recent applications of AI techniques; we will focus particularly on machine learning (ML), deep learning (DL), and hybrid methods, as these branches of AI are becoming increasingly attractive. Special attention will be paid to the recent development of the application of DL, as well as to the future trends in this topic.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Solar Radiation and Photovoltaics · Energy Load and Power Forecasting · Photovoltaic System Optimization Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
RELab, University of Jijel, Jijel 18000, Algeria
Dipartimento di Ingegneria e Architettura, University of Trieste, 34127 Trieste, Italy
Department of Energy, Politecnico di Milano, 20156 Milano, Italy
References (85)
Show source-provided references
1. IEA (2019, December 20). Sunspot of Global Markets. “Renewables 2018. Solar Energy”. Available online: https://www.iea.org/topics/renewables/solar/.
2. The Weather Intelligence for Renewable Energies benchmarking exercise on short-term forecasting of wind and solar power generation10.3390/en8099594 ↗
3. Pelland, S., Remund, J., Kleissl, J., Oozeki, T., and De Brabandere, K. (2013). Photovoltaic and Solar Forecasting: State of the Art, International Energy Agency. IEA PVPS Task 14, Subtask 3.1. Report Iea-PVPS T14–01: 2013.
4. Review of photovoltaic power forecasting10.1016/j.solener.2016.06.069 ↗
5. On recent advances in PV output power forecast10.1016/j.solener.2016.06.073 ↗
6. Photovoltaic and solar power forecasting for smart grid energy management10.17775/CSEEJPES.2015.00046 ↗
7. A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition10.1016/j.eswa.2012.01.039 ↗
8. Nespoli, A., Ogliari, E., Leva, S., Massi Pavan, A., Mellit, A., Lughi, V., and Dolara, A. (2019). Day-ahead photovoltaic forecasting: A comparison of the most effective techniques. Energies, 12.10.3390/en12091621 ↗
9. Comparing support vector regression for PV power forecasting to a physical modeling approach using measurement, numerical weather prediction, and cloud motion data10.1016/j.solener.2016.05.051 ↗
10. Comparison of different physical models for PV power output prediction10.1016/j.solener.2015.06.017 ↗
11. Day-ahead forecasting of solar power output from photovoltaic plants in the American Southwest10.1016/j.renene.2016.01.039 ↗
12. A solar time based analog ensemble method for regional solar power forecasting10.1109/TSTE.2018.2832634 ↗
13. Solar power prediction based on satellite images and support vector machine10.1109/TSTE.2016.2535466 ↗
14. Solar and photovoltaic forecasting through post-processing of the Global Environmental Multiscale numerical weather prediction model10.1002/pip.1180 ↗
15. Solar forecasting: Methods, challenges, and performance10.1109/MPE.2015.2461351 ↗
16. One-day-ahead daily power forecasting of photovoltaic systems based on partial functional linear regression models10.1016/j.renene.2016.04.089 ↗
17. PV power conversion and short-term forecasting in a tropical, densely-built environment in Singapore10.1016/j.renene.2016.03.075 ↗
18. Operational photovoltaics power forecasting using seasonal time series ensemble10.1016/j.solener.2018.02.011 ↗
19. Probabilistic Models for Spatio-Temporal Photovoltaic Power Forecasting10.1109/TSTE.2018.2847558 ↗
20. A probabilistic competitive ensemble method for short-term photovoltaic power forecasting10.1109/TSTE.2016.2610523 ↗
21. Probabilistic forecast of PV power generation based on higher order Markov chain10.1109/TPWRS.2016.2616902 ↗
22. Russell, S.J., and Norvig, P. (2009). Artificial Intelligence: A Modern Approach, Prentice-Hall, Inc.. [3rd ed.].
23. Artificial intelligence techniques for photovoltaic applications: A review10.1016/j.pecs.2008.01.001 ↗
24. A physical hybrid artificial neural network for short term forecasting of PV plant power output10.3390/en8021138 ↗
25. A hybrid model (SARIMA–SVM) for short-term power forecasting of a small-scale grid-connected photovoltaic plant10.1016/j.solener.2013.10.002 ↗
26. Very short-term photovoltaic power forecasting with cloud modeling: A review10.1016/j.rser.2016.10.068 ↗
27. Physical and hybrid methods comparison for the day ahead PV output power forecast10.1016/j.renene.2017.05.063 ↗
28. Forecasting of photovoltaic power generation and model optimization: A review10.1016/j.rser.2017.08.017 ↗
29. Solar photovoltaic generation forecasting methods: A review10.1016/j.enconman.2017.11.019 ↗
30. Review on forecasting of photovoltaic power generation based on machine learning and metaheuristic techniques10.1049/iet-rpg.2018.5649 ↗
31. Rich, E., and Knight, K. (1996). Artificial Intelligence, McGraw-Hill.
32. Deep learning10.1038/nature14539 ↗
33. Some Studies in Machine Learning Using the Game of Checkers
34. Alpaydin, E. (2016). Machine Learning: The New AI, MIT Press.
35. Haykin, S.S. (2009). Neural Networks and Learning Machines, Prentice Hall.
36. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.
37. Nielsen, M.A. (2015). Neural Networks and Deep Learning, Determination Press. [1st ed.].
38. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
39. Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv.10.3115/v1/D14-1179 ↗
40. Short-term forecasting of power production in a large-scale photovoltaic plant10.1016/j.solener.2014.03.018 ↗
41. A 24-h forecast of solar irradiance using artificial neural network: Application for performance prediction of a grid-connected PV plant at Trieste, Italy10.1016/j.solener.2010.02.006 ↗
42. Online 24-h solar power forecasting based on weather type classification using artificial neural network10.1016/j.solener.2011.08.027 ↗
43. Forecasting power output of photovoltaic systems based on weather classification and support vector machines10.1109/TIA.2012.2190816 ↗
44. Short-term power forecasting system for photovoltaic plants10.1016/j.renene.2012.01.108 ↗
45. Short–mid-term solar power prediction by using artificial neural networks10.1016/j.solener.2011.11.013 ↗
46. Use of support vector regression and numerically predicted cloudiness to forecast power output of a photovoltaic power plant in Kitakyushu, Japan10.1002/pip.1152 ↗
47. Short-term solar power prediction using a support vector machine10.1016/j.renene.2012.10.009 ↗
48. Photovoltaic power forecasting using statistical methods: Impact of weather data10.1049/iet-smt.2013.0135 ↗
49. A methodology based on dynamic artificial neural network for short-term forecasting of the power output of a PV generator10.1016/j.enconman.2014.05.090 ↗
50. An improved photovoltaic power forecasting model with the assistance of aerosol index data10.1109/TSTE.2014.2381224 ↗
51. Day-ahead hourly forecasting of power generation from photovoltaic plants10.1109/TSTE.2017.2762435 ↗
52. Day-ahead power output forecasting for small-scale solar photovoltaic electricity generators10.1109/TSG.2015.2397003 ↗
53. Day-ahead forecasting of solar photovoltaic output power using multilayer perceptron10.1007/s00521-016-2310-z ↗
54. Short-term forecasting of solar photovoltaic output power for tropical climate using ground-based measurement data10.1063/1.4962412 ↗
55. Multi-Model Ensemble for day ahead prediction of photovoltaic power generation10.1016/j.solener.2016.04.040 ↗
56. Li, Z., Rahman, S.M., Vega, R., and Dong, B. (2016). A hierarchical approach using machine learning methods in solar photovoltaic energy production forecasting. Energies, 9.10.3390/en9010055 ↗
57. Structured, physically inspired (gray box) models versus black box modeling for forecasting the output power of photovoltaic plants10.1016/j.energy.2017.01.015 ↗
58. Takagi–Sugeno fuzzy model-based approach considering multiple weather factors for the photovoltaic power short-term forecasting10.1049/iet-rpg.2016.1036 ↗
59. Das, U., Tey, K., Seyedmahmoudian, M., Idna Idris, M., Mekhilef, S., Horan, B., and Stojcevski, A. (2017). SVR-based model to forecast PV power generation under different weather conditions. Energies, 10.10.3390/en10070876 ↗
60. Analysis and validation of 24 hours ahead neural network forecasting of photovoltaic output power10.1016/j.matcom.2015.05.010 ↗
61. Data-driven upscaling methods for regional photovoltaic power estimation and forecast using satellite and numerical weather prediction data10.1016/j.solener.2017.09.068 ↗
62. Liu, W., Liu, C., Lin, Y., Ma, L., Xiong, F., and Li, J. (2018). Ultra-short-term forecast of photovoltaic output power under fog and haze weather. Energies, 11.10.3390/en11030528 ↗
63. Al-Dahidi, S., Ayadi, O., Adeeb, J., Alrbai, M., and Qawasmeh, B. (2018). Extreme Learning Machines for Solar Photovoltaic Power Predictions. Energies, 11.10.3390/en11102725 ↗
64. A novel photovoltaic power forecasting model based on echo state network10.1016/j.neucom.2018.10.022 ↗
65. A PV power interval forecasting based on seasonal model and nonparametric estimation algorithm10.1016/j.solener.2019.04.025 ↗
66. Accurate photovoltaic power forecasting models using deep LSTM-RNN
67. Son, J., Park, Y., Lee, J., and Kim, H. (2018). Sensorless PV power forecasting in grid-connected buildings through deep learning. Sensors, 18.10.3390/s18082529 ↗
68. A comparison of day-ahead photovoltaic power forecasting models based on deep learning neural network10.1016/j.apenergy.2019.113315 ↗
69. Lee, D., and Kim, K. (2019). Recurrent neural network-based hourly prediction of photovoltaic power output using meteorological information. Energies, 12.10.3390/en12020215 ↗
70. Assessment of forecasting techniques for solar power production with no exogenous inputs10.1016/j.solener.2012.04.004 ↗
71. Hybrid predictive models for accurate forecasting in PV systems10.3390/en6041918 ↗
72. Determination method of insolation prediction with fuzzy and applying neural network for long-term ahead PV power output correction10.1109/TSTE.2013.2246591 ↗
73. Short-term reforecasting of power output from a 48 MWe solar PV plant10.1016/j.solener.2014.11.017 ↗
74. One-day-ahead hourly forecasting for photovoltaic power generation using an intelligent method with weather-based forecasting models10.1049/iet-gtd.2015.0175 ↗
75. Deterministic and probabilistic forecasting of photovoltaic power based on deep convolutional neural network10.1016/j.enconman.2017.10.008 ↗
76. Dolara, A., Grimaccia, F., Leva, S., Mussetta, M., and Ogliari, E. (2018). Comparison of training approaches for photovoltaic forecasts by means of machine learning. Appl. Sci., 8.10.3390/app8020228 ↗
77. Solar photovoltaic power forecasting using optimized modified extreme learning machine technique
78. Short-term photovoltaic power forecasting using Artificial Neural Networks and an Analog Ensemble10.1016/j.renene.2017.02.052 ↗
79. Ogliari, E., Niccolai, A., Leva, S., and Zich, R. (2019). Computational intelligence techniques applied to the day ahead PV output power forecast: PHANN, SNO and mixed. Energies, 11.10.3390/en11061487 ↗
80. Nespoli, A., Ogliari, E., Dolara, A., Grimaccia, F., Leva, S., and Mussetta, M. (2018, January 8–13). Validation of ANN training approaches for day-ahead photovoltaic forecasts. Proceedings of the International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil.10.1109/IJCNN.2018.8489451 ↗
81. Hybrid method for short-term photovoltaic power forecasting based on deep convolutional neural network10.1049/iet-gtd.2018.5847 ↗
82. Short-term photovoltaic solar power forecasting using a hybrid Wavelet-PSO-SVM model based on SCADA and Meteorological information10.1016/j.renene.2017.11.011 ↗
83. Short-term PV power forecasting using hybrid GASVM technique10.1016/j.renene.2019.02.087 ↗
84. Day-ahead power forecasting in a large-scale photovoltaic plant based on weather classification using LSTM10.1016/j.energy.2019.07.168 ↗
85. Forecasting of PV plant output using hybrid wavelet-based LSTM-DNN structure model10.1049/iet-rpg.2018.5779 ↗