A Comprehensive Review on Ensemble Solar Power Forecasting Algorithms

다국어 초록 (Multilingual Abstract)

With increasing demand for energy, the penetration of alternative sources such as renewable energy in power grids has increased. Solar energy is one of the most common and well-known sources of energy in existing networks. But because of its non-stationary and non-linear characteristics, it needs to predict solar irradiance to provide more reliable Photovoltaic (PV) plants and manage the power of supply and demand. Although there are various methods to predict the solar irradiance. This paper gives the overview of recent studies with focus on solar irradiance forecasting with ensemble methods which are divided into two main categories: competitive and cooperative ensemble forecasting. In addition, parameter diversity and data diversity are considered as competitive ensemble forecasting and also preprocessing and post-processing are as cooperative ensemble forecasting. All these ensemble forecasting methods are investigated in this study. In the end, the conclusion has been drawn and the recommendations for future studies have been discussed.

참고문헌 (Reference)

1 Meenal R, "Weather forecasting for renewable energy system: a review" 2022

2 Ali M, "Variational mode decomposition based random forest model for solar radiation forecasting : new emerging machine learning technology" 7 : 6700-6717, 2021

3 Huertas Tato J, "Using smart persistence and random forests to predict photovoltaic energy production" 12 (12): 100-, 2018

4 Ahmad MW, "Tree-based ensemble methods for predicting PV power generation and their comparison with support vector regression" 164 : 465-474, 2018

5 Srivastava R, "Solar radiation forecasting using MARS, CART, M5, and random forest model : a case study for India" 5 (5): e02692-, 2019

6 Mukaram MZ, "Solar radiation forecast using hybrid SARIMA and ANN model: a case study at several locations in Peninsular Malaysia" 13 : 346-335, 2017

7 Behera MK, "Solar photovoltaic power forecasting using optimized modifi ed extreme learning machine technique" 21 (21): 428-438, 2018

8 Sobri S, "Solar photovoltaic generation forecasting methods : a review" 156 : 459-497, 2018

9 Kumar DS, "Solar irradiance resource and forecasting : a comprehensive review" 14 (14): 1641-1656, 2020

10 Arora I, "Solar irradiance forecasting using decision tree and ensemble models" IEEE 2020

11 Zhang G, "Solar forecasting with hourly updated numerical weather prediction" 154 : 111768-, 2022

12 He Y, "Short-term wind power prediction based on EEMD–LASSO–QRNN model" 105 : 107288-, 2021

13 Takeda H, "Short-term ensemble forecast for purchased photovoltaic generation" 149 : 176-187, 2017

14 Yadav HK, "Short-term PV power forecasting using empirical mode decomposition in integration with back-propagation neural network" 41 (41): 25-37, 2020

15 Zhang Na ; Ren Qiang ; Liu Guangchen ; Guo Liping ; Li Jingyu, "Short-term PV Output Power Forecasting Based on CEEMDAN-AE-GRU" 대한전기학회 17 (17): 1183-1194, 2022

16 Vaish J, "Short term load forecasting using ANN and ensemble models considering solar irradiance" IEEE 2020

17 Das UK, "SVR-based model to forecast PV power generation under different weather conditions" 10 (10): 876-, 2017

18 Van der Meer DW, "Review on probabilistic forecasting of photovoltaic power production and electricity consumption" 81 : 1484-1512, 2018

19 Diagne M, "Review of solar irradiance forecasting methods and a proposition for small-scale insular grids" 27 : 65-76, 2013

20 Sun Y, "Research on short-term module temperature prediction model based on BP neural network for photovoltaic power forecasting" 2015

21 REN21, "Renewables 2021 Global Status Report" 2021

22 Zervos A, "Renewables 2015 Global Status Report" 2015

23 (IRENA) I.R.E.A., "Renewable Capacity Statistics 2020"

24 Lee J, "Reliable solar irradiance prediction using ensemble learning-based models : a comparative study" 208 : 112582-, 2020

25 Kim H, "Probabilistic solar power forecasting based on bivariate conditional solar irradiation distributions" 12 (12): 2031-2041, 2021

26 David M, "Probabilistic forecasting of the solar irradiance with recursive ARMA and GARCH models" 133 : 55-72, 2016

27 Rodríguez F, "Predicting solar energy generation through artifi cial neural networks using weather forecasts for microgrid control" 126 : 855-864, 2018

28 Yang D, "Post-processing in solar forecasting : ten overarching thinking tools" 140 : 110735-, 2021

29 Jiranantacharoen P, "Photovoltaic power generation forecast by using estimator model and kalman filter" IEEE 2019

30 Wang H, "Photovoltaic power forecasting based on EEMD and a variable-weight combination forecasting model" 10 (10): 2627-, 2018

31 Reddy SS, "Optimal scheduling of thermal-wind-solar power system with storage" 101 : 1357-1368, 2017

32 Yang D, "Operational photovoltaics power forecasting using seasonal time series ensemble" 166 : 529-541, 2018

33 Chen C, "Online 24-h solar power forecasting based on weather type classifi cation using artifi cial neural network" 85 (85): 2856-2870, 2011

34 Raza MQ, "On recent advances in PV output power forecast" 136 : 125-144, 2016

35 Yang D, "On post-processing day-ahead NWP forecasts using Kalman filtering" 182 : 179-181, 2019

36 Park J, "Multistep-ahead solar radiation forecasting scheme based on the light gradient boosting machine : a case study of Jeju Island" 12 (12): 2271-, 2020

37 Persson C, "Multi-site solar power forecasting using gradient boosted regression trees" 150 : 423-436, 2017

38 Zhen Z, "Multi-level wavelet decomposition based day-ahead solar irradiance forecasting" IEEE 2018

39 Kim I, "Master Markov chain Monte Carlo and acceptancerejection algorithms for synthesising short-term variations in the generation output of the photovoltaic system" 11 (11): 878-888, 2017

40 Voyant C, "Machine learning methods for solar radiation forecasting : a review" 105 : 569-582, 2017

41 Flynn H, "Investigating the application of Kalman Filters for real-time accountancy in fusion fuel cycles" 176 : 113037-, 2022

42 Notton G et al, "Intermittent and stochastic character of renewable energy sources : consequences, cost of intermittence and benefi t of forecasting" 87 : 96-105, 2018

43 Fernández-Peruchena CM, "Increasing the temporal resolution of direct normal solar irradiance series in diff erent climatic zones" 115 : 255-263, 2015

44 Hajirahimi Z, "Hybridization of hybrid structures for time series forecasting : a review" 2022

45 Monjoly S, "Hourly forecasting of global solar radiation based on multiscale decomposition methods : a hybrid approach" 119 : 288-298, 2017

46 Wang F, "Generative adversarial networks and convolutional neural networks based weather classifi cation model for day ahead short-term photovoltaic power forecasting" 181 : 443-462, 2019

47 Gensler A, "Forecasting wind power-an ensemble technique with gradual coopetitive weighting based on weather situation" IEEE 2016

48 Vyas S, "Forecasting solar power generation on the basis of predictive and corrective maintenance activities"

49 Chiang P-H, "Forecasting of solar photovoltaic system power generation using wavelet decomposition and biascompensated random forest" 2017

50 Das UK, "Forecasting of photovoltaic power generation and model optimization : a review" 81 : 912-928, 2018

51 Malvoni M, "Forecasting of PV Power Generation using weather input data-preprocessing techniques" 126 : 651-658, 2017

52 Nilam B, "Forecasting geomagnetic activity (Dst Index) using the ensemble kalman filter" 511 (511): 723-731, 2022

53 Sharma A, "Forecasting daily global solar irradiance generation using machine learning" 82 : 2269-, 2018

54 Kumari P, "Extreme gradient boosting and deep neural network based ensemble learning approach to forecast hourly solar irradiance" 279 : 123285-, 2021

55 De Giorgi MG, "Error analysis of hybrid photovoltaic power forecasting models : a case study of mediterranean climate" 100 : 117-130, 2015

56 Ren Y, "Ensemble methods for wind and solar power forecasting—A state-of-the-art review" 50 : 82-91, 2015

57 Polikar R, "Ensemble learning in ensemble machine learning : methods and applications" Springer 2012

58 Ribeiro MHDM, "Ensemble approach based on bagging, boosting and stacking for shortterm prediction in agribusiness time series" 2020 (2020): 105837-, 2020

59 Hong T, "Energy forecasting : a review and outlook" 7 : 376-388, 2020

60 Ribeiro MHDM, "Effi cient bootstrap stacking ensemble learning model applied to wind power generation forecasting" 136 : 107712-, 2022

61 Vignola F, "Effects of changing spectral radiation distribution on the performance of photodiode pyranometers" 129 : 224-235, 2016

62 Prasad R, "Designing a multi-stage multivariate empirical mode decomposition coupled with ant colony optimization and random forest model to forecast monthly solar radiation" 236 : 778-792, 2019

63 Kumari P, "Deep learning models for solar irradiance forecasting : a comprehensive review" 318 : 128566-, 2021

64 Gao M, "Day-ahead power forecasting in a large-scale photovoltaic plant based on weather classifi cation using LSTM" 187 : 115838-, 2019

65 Meng M, "Daily photovoltaic power generation forecasting model based on random forest algorithm for north China in winter" 12 (12): 2247-, 2020

66 McCandless T, "Comparison of implicit vs explicit regime identifi cation in machine learning methods for solar irradiance prediction" 13 (13): 689-, 2020

67 Liu H, "Comparison of four Adaboost algorithm based artifi cial neural networks in wind speed predictions" 92 : 67-81, 2015

68 Fan J, "Comparison of Support Vector Machine and Extreme Gradient Boosting for predicting daily global solar radiation using temperature and precipitation in humid subtropical climates : a case study in China" 164 : 102-111, 2018

69 Panamtash H, "Coherent probabilistic solar power forecasting" IEEE 2018

70 Yang B, "Classification and summarization of solar irradiance and power forecasting methods: A thorough review" Power System Technology Press 2021

71 Tyralis H, "Boosting algorithms in energy research : a systematic review" 33 (33): 14101-14117, 2021

72 Kaur A, "Benefi ts of solar forecasting for energy imbalance markets" 86 : 819-830, 2016

73 Breiman L, "Bagging predictors" 24 (24): 123-140, 1996

74 Yagli GM, "Automatic hourly solar forecasting using machine learning models" 105 : 487-498, 2019

75 Pedro HT, "Assessment of machine learning techniques for deterministic and probabilistic intra-hour solar forecasts" 123 : 191-203, 2018

76 Bokde N, "Analysis of diff erencing and decomposition preprocessing methods for wind speed prediction" 71 : 926-938, 2018

77 Mitrentsis G, "An interpretable probabilistic model for short-term solar power forecasting using natural gradient boosting" 309 : 118473-, 2022

78 Choi S, "An ensemble learner-based bagging model using past output data for photovoltaic forecasting" 13 (13): 1438-, 2020

79 Acharya SK, "An Ensemble Learning Method for Solar Power Forecasting" 8 (8): 1310-1311, 2018

80 Mellit A, "Advanced methods for photovoltaic output power forecasting : a review" 10 (10): 487-, 2020

81 D eo RC, "A wavelet-coupled support vector machine model for forecasting global incident solar radiation using limited meteorological dataset" 168 : 568-593, 2016

82 AlSkaif T, "A systematic analysis of meteorological variables for PV output power estimation" 153 : 12-22, 2020

83 Li B, "A review on the integration of probabilistic solar forecasting in power systems" 210 : 68-86, 2020

84 Bokde N, "A review on hybrid empirical mode decomposition models for wind speed and wind power prediction" 12 (12): 254-, 2019

85 Ahmed R, "A review and evaluation of the state-of-theart in PV solar power forecasting : techniques and optimization" 124 : 109792-, 2020

86 Gupta A, "A review and evaluation of solar forecasting technologies" 47 : 2420-2425, 2021

87 Bracale A, "A probabilistic competitive ensemble method for short-term photovoltaic power forecasting" 8 (8): 551-560, 2016

88 Zhu H, "A power prediction method for photovoltaic power plant based on wavelet decomposition and artifi cial neural networks" 9 (9): 11-, 2015

89 Gürtürk M, "A novel approach to investigate the effects of global warming and exchange rate on the solar power plants" 239 : 122344-, 2022

90 Zhang W, "A new solar power output prediction based on hybrid forecast engine and decomposition model" 81 : 105-120, 2018

91 Basaran K, "A new approach for prediction of solar radiation with using ensemble learning algorithm" 44 (44): 7159-7171, 2019

92 Wang F, "A minutely solar irradiance forecasting method based on real-time sky image-irradiance mapping model" 220 : 113075-, 2020

93 Hussain S, "A hybrid solar radiation modeling approach using wavelet multiresolution analysis and artificial neural networks" 208 : 540-550, 2017

94 Belmahdi B, "A hybrid ARIMA–ANN method to forecast daily global solar radiation in three diff erent cities in Morocco" 135 (135): 1-23, 2020

95 Taieb SB, "A gradient boosting approach to the Kaggle load forecasting competition" 30 (30): 382-394, 2014

96 Lai CS, "A deep learning based hybrid method for hourly solar radiation forecasting" 177 : 114941-, 2021

97 Blaga R, "A current perspective on the accuracy of incoming solar energy forecasting" 70 : 119-144, 2019

98 Guermoui M, "A comprehensive review of hybrid models for solar radiation forecasting" 258 : 120357-, 2020

99 Singla P, "A comprehensive review and analysis of solar forecasting techniques" 16 (16): 187-223, 2022

100 Shaik AB, "A brief survey on random forest ensembles in classifi cation model" Springer 2019

101 Usman Munawar ; Zhanle Wang, "A Framework of Using Machine Learning Approaches for Short‑Term Solar Power Forecasting" 대한전기학회 15 (15): 561-569, 2020

102 Moon J, "A Comparative analysis of tree-based models for day-ahead solar irradiance forecasting" 2021