Decomposition-Ensemble Learning Approach in Solar Radiation Forecasting

Öz

The amount of electrical energy to be obtained from solar energy systems varies greatly depending on the solar radiation value. The design and planning of a solar energy system are possible by knowing the radiation value. Since solar radiation intensity has a highly variable structure throughout the day, it is very difficult to capture these changes using a single prediction model. In this context, in recent years, different hybrid models and approaches have been proposed by researchers to overcome the limitations of single models and increase predictive accuracy. In this study, the applicability and performance of the method were investigated by using the Decomposition-Ensemble learning approach, which is a hybrid approach to the estimation of solar radiation intensity data. In addition, it is aimed to increase the time resolution of forwarding solar radiation forecasts. In this context, 15-day solar radiation value was forecasted hourly, using an annual solar radiation data measured hourly with a pyranometer located within Afyon Kocatepe University, Solar and Wind Energy Application and Research Center. In the learning approach, Empirical Mode Decomposition (EMD) method is used for decomposition and Least Squares Support Vector Regression (LS-SVR) method is used for individual predictions. The most appropriate parameter values of LS-SVR models were determined by using a grid search algorithm and 5 fold cross-validation methods. The results obtained from the study showed that the Decomposition-Ensemble learning approach is successful in estimating solar radiation data.

Anahtar Kelimeler

• Solar radiation forecasting
• decomposition-ensemble learning approach
• least squares support vector machines (LS-SVM)
• empirical mode decomposition (EMD)

Güneş Işınımı Tahmininde Ayrıştırma-Birleştirme Öğrenme Yaklaşımı

Öz

Güneş enerjisi sistemlerinden elde edilecek elektrik enerjisi miktarı büyük oranda güneş ışınım değerine bağlı olarak değişmektedir. Bir güneş enerji sisteminin tasarımı ve planlaması, ışınım değerinin bilinmesi ile mümkündür. Güneş ışınım şiddetinin gün içerisinde yüksek değişkenlik gösteren bir yapıya sahip olması nedeniyle tek bir tahmin modeli kullanılarak bu değişimlerin yakalanması oldukça güçtür. Bu bağlamda, son yıllarda araştırmacılar tarafından tekli modellerin sınırlamalarının üstesinden gelmek ve öngörme hassasiyetini artırmak için farklı hibrit modeller ve yaklaşımlar önerilmiştir. Bu çalışmada, güneş ışınım şiddeti verilerinin tahmininde hibrit bir yaklaşım olan Ayrıştırma-Birleştirme öğrenme yaklaşımı kullanılarak yöntemin uygulanabilirliği ve performansı araştırılmıştır. Ayrıca ileriye yönelik güneş ışınımı tahminlerinin zaman çözünürlüğünün arttırılması amaçlanmıştır. Bu kapsamda Afyon Kocatepe Üniversitesi, Güneş ve Rüzgâr Enerjisi Uygulama ve Araştırma Merkezi bünyesinde yer alan bir piranometre ile saatlik olarak ölçülmüş bir yıllık güneş ışınım verisi kullanılarak 15 günlük güneş ışınımı değeri saatlik olarak tahmin edilmiştir. Öğrenme yaklaşımında ayrıştırma işlemi için Ampirik Kip Ayrışımı (AKA), bireysel tahminler için ise En Küçük Kareler Destek Vektör Regresyon (EKK-DVR) yöntemleri kullanılmıştır. EKK-DVR modellerinin en uygun parametre değerleri grid arama algoritması ve 5 katlamalı çapraz doğrulama yöntemleri kullanılarak belirlenmiştir. Çalışmadan elde edilen sonuçlar Ayrıştırma-Birleştirme öğrenme yaklaşımının güneş ışınım verilerinin tahmininde başarılı olduğunu göstermiştir.

Anahtar Kelimeler

• Güneş ışınımı tahmini
• ayrıştırma-birleştirme öğrenme yaklaşımı
• ampirik kip ayrışımı (AKA)
• en küçük kareler destek vektör makineleri (EKK-DVR)

Kaynakça

1. Akarslan E, Hocaoǧlu FO, Edizkan R, 2014. A novel M-D (multi-dimensional) linear prediction filter approach for hourly solar radiation forecasting. Energy, 73, 978–986. https://doi.org/10.1016/j.energy.2014.06.113
2. Alsina EF, Bortolini M, Gamberi M, Regattieri A, 2016. Artificial neural network optimisation for monthly average daily global solar radiation prediction. Energy Conversion and Management, 120, 320–329. https://doi.org/10.1016/j.enconman.2016.04.101
3. Altan A, Karasu S, Bekiros S, 2019. Digital currency forecasting with chaotic meta-heuristic bio-inspired signal processing techniques. Chaos, Solitons and Fractals, 126, 325–336. https://doi.org/10.1016/j.chaos.2019.07.011
4. Alvanitopoulos PF, Andreadis I, Georgoulas N, Zervakis M, Nikolaidis N, 2014. Solar radiation prediction model based on Empirical Mode Decomposition. IST 2014 - 2014 IEEE International Conference on Imaging Systems and Techniques, Proceedings, 161–166. https://doi.org/10.1109/IST.2014.6958466
5. Behrang MA, Assareh E, Ghanbarzadeh A, Noghrehabadi AR, 2010. The potential of different artificial neural network (ANN) techniques in daily global solar radiation modeling based on meteorological data. Solar Energy, 84(8), 1468–1480. https://doi.org/10.1016/j.solener.2010.05.009
6. Belaid S, Mellit A, 2016. Prediction of daily and mean monthly global solar radiation using support vector machine in an arid climate. Energy Conversion and Management, 118, 105–118. https://doi.org/10.1016/j.enconman.2016.03.082
7. Bracale A, Caramia P, Carpinelli G, Di Fazio AR, Ferruzzi G, 2013. A Bayesian method for Short-Term probabilistic forecasting of photovoltaic generation in smart grid operation and control. Energies, 6(2), 733–747. https://doi.org/10.3390/en6020733
8. Cao JC, Cao SH, 2006. Study of forecasting solar irradiance using neural networks with preprocessing sample data by wavelet analysis. Energy, 31(15), 3435–3445. https://doi.org/10.1016/j.energy.2006.04.001

9. Chen JL, Li GS, Wu SJ, 2013. Assessing the potential of support vector machine for estimating daily solar radiation using sunshine duration. Energy Conversion and Management, 75, 311–318. https://doi.org/10.1016/j.enconman.2013.06.034
10. Chen S, Gooi HB, Wang MQ, 2013. Solar radiation forecast based on fuzzy logic and neural networks. Renewable Energy, 60, 195–201. https://doi.org/10.1016/j.renene.2013.05.011
11. Chu Y, Pedro HTC, Coimbra CFM, 2013. Hybrid intra-hour DNI forecasts with sky image processing enhanced by stochastic learning. Solar Energy, 98(PC), 592–603. https://doi.org/10.1016/j.solener.2013.10.020
12. Dong Z, Yang D, Reindl T, Walsh WM, 2013. Short-term solar irradiance forecasting using exponential smoothing state space model. Energy, 55, 1104–1113. https://doi.org/10.1016/j.energy.2013.04.027
13. Eroğlu H, 2018. The Suitability Map Determination for Solar Power Plants: A Case Study. Journal of the Institute of Science and Technology, 8(4), 97–106. https://doi.org/10.21597/jist.430615
14. Genç, A. 2018. Denim Kumaşın Laminasyon Teknikleriyle Fonksiyonelleştirilmesinin Araştırılması, İnönü Üniversitesi Fen Bilimleri Enstitüsü, Yüksek Lisans Tezi (Basılmış). https://tez.yok.gov.tr/UlusalTezMerkezi/tezSorguSonucYeni.jsp
15. Guermoui M, Abdelaziz R, Gairaa K, Djemoui L, Benkaciali S, 2020. New temperature-based predicting model for global solar radiation using support vector regression. International Journal of Ambient Energy, 1–11. https://doi.org/10.1080/01430750.2019.1708792
16. Hocaoĝlu FO, 2011. Stochastic approach for daily solar radiation modeling. Solar Energy, 85(2), 278–287. https://doi.org/10.1016/j.solener.2010.12.003
17. Hocaoglu FO, Serttas F, 2017. A novel hybrid (Mycielski-Markov) model for hourly solar radiation forecasting. Renewable Energy, 108, 635–643. https://doi.org/10.1016/j.renene.2016.08.058
18. Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, Liu HH, 1998. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, 454(1971), 903–995. https://doi.org/10.1098/rspa.1998.0193
19. Ji W, Chee KC, 2011. Prediction of hourly solar radiation using a novel hybrid model of ARMA and TDNN. Solar Energy, 85(5), 808–817. https://doi.org/10.1016/j.solener.2011.01.013
20. Karasu S, Altan A, 2019. Recognition Model for Solar Radiation Time Series based on Random Forest with Feature Selection Approach. ELECO 2019 - 11th International Conference on Electrical and Electronics Engineering, 8–11. https://doi.org/10.23919/ELECO47770.2019.8990664
21. Karasu S, Altan A, Sarac Z, Hacioglu R, 2017. PREDICTION OF SOLAR RADIATION BASED ON MACHINE LEARNING METHODS. In The Journal of Cognitive Systems, 2(1), 16-20. www.dergipark.gov.tr/jcs
22. Koç A, Yağlı H, Koç Y, Uğurlu İ, 2018. Dünyada ve Türkiye’de Enerji Görünümünün Genel Değerlendirilmesi. In Mühendis ve Makina, 59 (692) , 86-114. https://dergipark.org.tr/tr/pub/muhendismakina/issue/48388/614281
23. Kok B, Benli H, 2017. Energy diversity and nuclear energy for sustainable development in Turkey. Renewable Energy, 111, 870–877. https://doi.org/10.1016/j.renene.2017.05.001
24. Lazarevska E, 2016. Neural network approach based on convex incremental learning machine for prediction of diffuse solar radiation. International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, 2016-December, 29–36. https://doi.org/10.1109/ICUMT.2016.7765228
25. Li FF, Wang SY, Wei JH, 2018. Long term rolling prediction model for solar radiation combining empirical mode decomposition (EMD) and artificial neural network (ANN) techniques. Journal of Renewable and Sustainable Energy, 10(1), 013704. https://doi.org/10.1063/1.4999240
26. Li Q, Meng Q, Cai J, Yoshino H, Mochida A, 2009. Predicting hourly cooling load in the building: A comparison of support vector machine and different artificial neural networks. Energy Conversion and Management, 50(1), 90–96. https://doi.org/10.1016/j.enconman.2008.08.033
27. Lu CJ, Lee TS, Chiu CC, 2009. Financial time series forecasting using independent component analysis and support vector regression. Decision Support Systems, 47(2), 115–125. https://doi.org/10.1016/j.dss.2009.02.001
28. Lu W, Wang W, Leung AYT, Lo SM, Yuen RKK, Xu Z, Fan H, 2002. Air pollutant parameter forecasting using support vector machines. Proceedings of the International Joint Conference on Neural Networks, 1, 630–635. https://doi.org/10.1109/ijcnn.2002.1005545
29. Mecibah MS, Boukelia TE, Tahtah R, Gairaa K, 2014. Introducing the best model for estimation the monthly mean daily global solar radiation on a horizontal surface (Case study: Algeria). Renewable and Sustainable Energy Reviews, Vol. 36, pp. 194–202. https://doi.org/10.1016/j.rser.2014.04.054
30. Meenal R, Selvakumar AI, 2018. Assessment of SVM, empirical and ANN based solar radiation prediction models with most influencing input parameters. Renewable Energy, 121, 324–343. https://doi.org/10.1016/j.renene.2017.12.005
31. Mellit A, Benghanem M, Kalogirou SA, 2006. An adaptive wavelet-network model for forecasting daily total solar-radiation. Applied Energy, 83(7), 705–722. https://doi.org/10.1016/j.apenergy.2005.06.003
32. Moghaddamnia A, Remesan R, Kashani MH, Mohammadi M, Han D, Piri J, 2009. Comparison of LLR, MLP, Elman, NNARX and ANFIS Models-with a case study in solar radiation estimation. Journal of Atmospheric and Solar-Terrestrial Physics, 71(8–9), 975–982. https://doi.org/10.1016/j.jastp.2009.04.009
33. Mokhtarzad M, Eskandari F, Jamshidi VN, Arabasadi A, 2017. Drought forecasting by ANN, ANFIS, and SVM and comparison of the models. Environmental Earth Sciences, 76(21), 1–10. https://doi.org/10.1007/s12665-017-7064-0
34. Monjoly S, André M, Calif R, Soubdhan T, 2017. Hourly forecasting of global solar radiation based on multiscale decomposition methods: A hybrid approach. Energy, 119, 288–298. https://doi.org/10.1016/j.energy.2016.11.061
35. Pelckmans K, Suykens JA, Van Gestel T, De Brabanter J, Lukas L, Hamers B, Vandewalle J, (2002). LS-SVMlab: a matlab/c toolbox for least squares support vector machines. Tutorial. KULeuven-ESAT. Leuven, Belgium, 142(1–2).
36. Piri J, Shamshirband S, Petković D, Tong CW, Rehman MHU, 2015. Prediction of the solar radiation on the Earth using support vector regression technique. Infrared Physics and Technology, 68, 179–185. https://doi.org/10.1016/j.infrared.2014.12.006
37. Rato RT, Ortigueira MD, Batista AG, 2008. On the HHT, its problems, and some solutions. Mechanical Systems and Signal Processing, 22(6), 1374–1394. https://doi.org/10.1016/j.ymssp.2007.11.028
38. Sun S, Wang S, Zhang G, Zheng J, 2018. A decomposition-clustering-ensemble learning approach for solar radiation forecasting. Solar Energy, 163, 189–199. https://doi.org/10.1016/j.solener.2018.02.006
39. Suykens JAK, Van GT, Brabanter JD, Moor BD, Vandewalle J, 2002. Least Squares Support Vector Machines. World Scientific, Singapore. Singapore: World Scientific Pub. Co.
40. Trapero JR, Kourentzes N, Martin A, 2015. Short-term solar irradiation forecasting based on dynamic harmonic regression. Energy, 84, 289–295. https://doi.org/10.1016/j.energy.2015.02.100
41. Vapnik V, 2013. The nature of statistical learning theory. Springer science & business media.
42. Voyant C, Muselli M, Paoli C, Nivet ML, 2012. Numerical weather prediction (NWP) and hybrid ARMA/ANN model to predict global radiation. Energy, 39(1), 341–355. https://doi.org/10.1016/j.energy.2012.01.006
43. Yadav AK, Chandel SS, 2014. Solar radiation prediction using Artificial Neural Network techniques: A review. Renewable and Sustainable Energy Reviews, Vol. 33, pp. 772–781. https://doi.org/10.1016/j.rser.2013.08.055
44. Yang D, Ye Z, Lim LHI, Dong Z, 2015. Very short term irradiance forecasting using the lasso. Solar Energy, 114, 314–326. https://doi.org/10.1016/j.solener.2015.01.016
45. Yao W, Zhang C, Hao H, Wang X, Li X, 2018. A support vector machine approach to estimate global solar radiation with the influence of fog and haze. Renewable Energy, 128, 155–162. https://doi.org/10.1016/j.renene.2018.05.069