Hybrid method for shortterm photovoltaic power forecasting based on deep convolutional neural network
Hybrid method for shortterm photovoltaic power forecasting based on deep convolutional neural network
 Author(s): Haixiang Zang^{ 1} ; Lilin Cheng^{ 1} ; Tao Ding^{ 2} ; Kwok W. Cheung^{ 3} ; Zhi Liang^{ 1} ; Zhinong Wei^{ 1} ; Guoqiang Sun^{ 1}
 DOI: 10.1049/ietgtd.2018.5847
For access to this article, please select a purchase option:
Buy article PDF
Buy Knowledge Pack
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Thank you
Your recommendation has been sent to your librarian.
 Author(s): Haixiang Zang^{ 1} ; Lilin Cheng^{ 1} ; Tao Ding^{ 2} ; Kwok W. Cheung^{ 3} ; Zhi Liang^{ 1} ; Zhinong Wei^{ 1} ; Guoqiang Sun^{ 1}


View affiliations

Affiliations:
1:
College of Energy and Electrical Engineering , Hohai University , Nanjing 210098 , People's Republic of China ;
2: Department of Electrical Engineering , Xi'an Jiaotong University , Xi'an 710049 , People's Republic of China ;
3: GE Grid Solutions, Redmond, WA 98052 , USA

Affiliations:
1:
College of Energy and Electrical Engineering , Hohai University , Nanjing 210098 , People's Republic of China ;
 Source:
Volume 12, Issue 20,
13
November
2018,
p.
4557 – 4567
DOI: 10.1049/ietgtd.2018.5847 , Print ISSN 17518687, Online ISSN 17518695
Photovoltaic (PV) electric power has been widely employed to satisfy rising energy demands because inexhaustible renewable energy is environmentally friendly. In order to mitigate the impact caused by the uncertainty of solar radiation in gridconnected PV systems, a hybrid method based on a deep convolutional neural network (CNN) is introduced for shortterm PV power forecasting. In the proposed method, different frequency components are first decomposed from the historical time series of PV power through variational mode decomposition (VMD). Then, they are constructed into a twodimensional data form with correlations in both daily and hourly timescales that can be extracted by convolution kernels. Moreover, the time series of residue from VMD is refined into advanced features by a CNN, which could reduce the data size and be easier for further model training along with meteorological elements. The hybrid model has been verified by forecasting the output power of PV arrays with diverse capacities in various hourly timescales, which demonstrates its superiority over commonly used methods.
Inspec keywords: time series; photovoltaic power systems; power engineering computing; neural nets; load forecasting
Other keywords: photovoltaic electric power; rising energy demands; solar radiation; convolution kernels; gridconnected PV systems; deep convolutional neural network; hourly timescales; historical time series; shortterm PV power forecasting; commonly used methods; VMD; hybrid model; shortterm photovoltaic power forecasting; different frequency components; inexhaustible renewable energy; hybrid method; CNN; variational mode decomposition
Subjects: Optimisation techniques; Knowledge engineering techniques; Interpolation and function approximation (numerical analysis); Other topics in statistics; Power engineering computing; Other topics in statistics; Solar power stations and photovoltaic power systems; Neural computing techniques
References


1)

1. Hernandez, R.R., Easter, S.B., MurphyMariscal, M.L., et al: ‘Environmental impacts of utilityscale solar energy’, Renew. Sustain. Energy Rev., 2014, 29, pp. 766–779.


2)

2. Timilsina, G.R., Kurdgelashvili, L., Narbel, P.A.: ‘Solar energy: markets, economics and policies’, Renew. Sustain. Energy Rev., 2012, 16, (1), pp. 449–465.


3)

3. Fonseca, J.G.D., Oozeki, T., Takashima, T., et al: ‘Use of support vector regression and numerically predicted cloudiness to forecast power output of a photovoltaic power plant in Kitakyushu, Japan’, Prog. Photovolt., 2012, 20, (7), pp. 874–882.


4)

4. Jiang, H., Dong, Y.: ‘A nonlinear support vector machine model with hard penalty function based on glowworm swarm optimization for forecasting daily global solar radiation’, Energy Convers. Manage., 2016, 126, pp. 991–1002.


5)

5. Wolff, B., Kuhnert, J., Lorenz, E., et al: ‘Comparing support vector regression for Pv power forecasting to a physical modeling approach using measurement, numerical weather prediction, and cloud motion data’, Sol. Energy, 2016, 135, pp. 197–208.


6)

6. De Leone, R., Pietrini, M., Giovannelli, A.: ‘Photovoltaic energy production forecast using support vector regression’, Neural Comput. Appl., 2015, 26, (8), pp. 1955–1962.


7)

7. SalcedoSanz, S., CasanovaMateo, C., MunozMari, J., et al: ‘Prediction of daily global solar irradiation using temporal Gaussian processes’, IEEE Geosci. Remote Sens. Lett., 2014, 11, (11), pp. 1936–1940.


8)

8. Sheng, H.M., Xiao, J., Cheng, Y.H., et al: ‘Shortterm solar power forecasting based on weighted Gaussian process regression’, IEEE Trans. Ind. Electron., 2018, 65, (1), pp. 300–308.


9)

9. Rohani, A., Taki, M., Abdollahpour, M.: ‘A novel soft computing model (Gaussian process regression with Kfold cross validation) for daily and monthly solar radiation forecasting (part: I)’, Renew. Energy, 2018, 115, pp. 411–422.


10)

10. Urraca, R., Antonanzas, J., AliaMartinez, M., et al: ‘Smart baseline models for solar irradiation forecasting’, Energy Convers. Manage., 2016, 108, pp. 539–548.


11)

11. Hassan, M.A., Khalil, A., Kaseb, S., et al: ‘Exploring the potential of treebased ensemble methods in solar radiation modeling’, Appl. Energy, 2017, 203, pp. 897–916.


12)

12. Nagy, G.I., Barta, G., Kazi, S., et al: ‘Gefcom2014: probabilistic solar and wind power forecasting using a generalized additive tree ensemble approach’, Int. J. Forecast., 2016, 32, (3), pp. 1087–1093.


13)

13. Bouzerdoum, M., Mellit, A., Pavan, A.M.: ‘A hybrid model (SarimaSvm) for shortterm power forecasting of a smallscale gridconnected photovoltaic plant’, Sol. Energy, 2013, 98, pp. 226–235.


14)

14. De Giorgi, M.G., Malvoni, M., Congedo, P.M.: ‘Comparison of strategies for multistep ahead photovoltaic power forecasting models based on hybrid group method of data handling networks and least square support vector machine’, Energy, 2016, 107, pp. 360–373.


15)

15. Li, J.M., Ward, J.K., Tong, J.N., et al: ‘Machine learning for solar irradiance forecasting of photovoltaic system’, Renew. Energy, 2016, 90, pp. 542–553.


16)

16. Huang, C.M., Chen, S.J., Yang, S.P., et al: ‘Onedayahead hourly forecasting for photovoltaic power generation using an intelligent method with weatherbased forecasting models’, IET Gener. Transm. Distrib., 2015, 9, (14), pp. 1874–1882.


17)

17. Wu, Q.L., Peng, C.Y.: ‘Wind power generation forecasting using least squares support vector machine combined with ensemble empirical mode decomposition, principal component analysis and a bat algorithm’, Energies, 2016, 9, (4), pp. 1–19.


18)

18. De Giorgi, M.G., Congedo, P.M., Malvoni, M., et al: ‘Error analysis of hybrid photovoltaic power forecasting models: a case study of Mediterranean climate’, Energy Convers. Manage., 2015, 100, pp. 117–130.


19)

19. Sivavaraprasad, G., Ratnam, D.V.: ‘Shortterm forecasting of ionospheric total electron content over a lowlatitude global navigation satellite system station’, IET Radar Sonar Navig.., 2017, 11, (8), pp. 1309–1320.


20)

20. Monjoly, S., Andre, M., Calif, R., et al: ‘Hourly forecasting of global solar radiation based on multiscale decomposition methods: a hybrid approach’, Energy, 2017, 119, pp. 288–298.


21)

21. Gao, X.M., Yang, S.F., Pan, S.B.: ‘Optimal parameter selection for support vector machine based on artificial bee colony algorithm: a case study of gridconnected PV system power prediction’, Comput. Intell. Neurosci., 2017, 2017, pp. 1–14.


22)

22. Wang, D.Y., Luo, H.Y., Grunder, O., et al: ‘Multistep ahead electricity price forecasting using a hybrid model based on twolayer decomposition technique and Bp neural network optimized by firefly algorithm’, Appl. Energy, 2017, 190, pp. 390–407.


23)

23. Abdoos, A.A.: ‘A new intelligent method based on combination of Vmd and Elm for short term wind power forecasting’, Neurocomputing, 2016, 203, pp. 111–120.


24)

24. Wang, D.Y., Wei, S., Luo, H.Y., et al: ‘A novel hybrid model for air quality index forecasting based on twophase decomposition technique and modified extreme learning machine’, Sci. Total Environ., 2017, 580, pp. 719–733.


25)

25. Yang, W.X., Peng, Z.K., Wei, K.X., et al: ‘Superiorities of variational mode decomposition over empirical mode decomposition particularly in timefrequency feature extraction and wind turbine condition monitoring’, IET Renew. Power Gener., 2017, 11, (4), pp. 443–452.


26)

26. Wang, H.Z., Wang, G.B., Li, G.Q., et al: ‘Deep belief network based deterministic and probabilistic wind speed forecasting approach’, Appl. Energy, 2016, 182, pp. 80–93.


27)

27. Qureshi, A.S., Khan, A., Zameer, A., et al: ‘Wind power prediction using deep neural network based meta regression and transfer learning’, Appl. Soft Comput., 2017, 58, pp. 742–755.


28)

28. Zhao, Z., Chen, W.H., Wu, X.M., et al: ‘Lstm network: a deep learning approach for shortterm traffic forecast’, IET Intell. Transp. Syst., 2017, 11, (2), pp. 68–75.


29)

29. Ji, S.W., Xu, W., Yang, M., et al: ‘3d convolutional neural networks for human action recognition’, IEEE Trans. Pattern Anal. Mach. Intell., 2013, 35, (1), pp. 221–231.


30)

30. Wang, H.Z., Li, G.Q., Wang, G.B., et al: ‘Deep learning based ensemble approach for probabilistic wind power forecasting’, Appl. Energy, 2017, 188, pp. 56–70.


31)

31. Dragomiretskiy, K., Zosso, D.: ‘Variational mode decomposition’, IEEE Trans. Signal Process., 2014, 62, (3), pp. 531–544.


32)

32. Lahmiri, S.: ‘Comparing variational and empirical mode decomposition in forecasting dayahead energy prices’, IEEE Syst. J., 2017, 11, (3), pp. 1907–1910.


33)

33. Lahmiri, S.: ‘Intraday stock price forecasting based on variational mode decomposition’, J. Comput. Sci., 2016, 12, pp. 23–27.


34)

34. Li, C., Liang, M.: ‘Extraction of oil debris signature using integral enhanced empirical mode decomposition and correlated reconstruction’, Meas. Sci. Technol., 2011, 22, (8), pp. 1–10.


35)

35. Daw, N.W.: ‘The foundations of development and deprivation in the visual system’, J. Physiol.London, 2009, 587, (12), pp. 2769–2773.


36)

36. Anthimopoulos, M., Christodoulidis, S., Ebner, L., et al: ‘Lung pattern classification for interstitial lung diseases using a deep convolutional neural network’, IEEE Trans. Med. Imaging, 2016, 35, (5), pp. 1207–1216.


37)

37. Zubair, S., Yan, F., Wang, W.W.: ‘Dictionary learning based sparse coefficients for audio classification with max and average pooling’, Digit. Signal Process., 2013, 23, (3), pp. 960–970.


38)

38. Karpathy, A., Toderici, G., Shetty, S., et al: ‘Largescale video classification with convolutional neural networks’. 2014 IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA, June 2014, pp. 1725–1732.


39)

39. Bergstra, J., Bengio, Y.: ‘Random search for hyperparameter optimization’, J. Mach. Learn. Res., 2012, 13, pp. 281–305.


40)

40. Steenwijk, M.D., Daams, M., Barkhof, F., et al: ‘Multiview convolutional neural networks using batch normalization outperform human raters during automatic white matter lesion segmentation’, Mult. Scler. J., 2017, 23, pp. 558–559.


41)

41. Abadi, M.: ‘Tensorflow: learning functions at scale’, ACM Sigplan Not., 2016, 51, (9), pp. 1–1.


42)

42. Li, A., Li, Y.X., Li, X.H.: ‘Tensorflow and Kerasbased convolutional neural network in cat image recognition’. 2017 2nd Int. Conf. Computational Modeling, Simulation and Applied Mathematics (Cmsam), 2017, pp. 529–533.


1)