Abstract
Forecasting solar irradiation is very important to plane and size PV systems. In this paper, the fully complex valued wavelet network (FCWN) for forecasting the global solar irradiation is proposed. The complex valued gradient descent-learning algorithm is used to find the optimal complex-valued parameters of the network. An improved fully wavelet function is proposed and used as an activation function of the hidden neurons of the FCWN. The meteorological measured data of Tamanrasset city, Algeria (latitude: \(22^{\circ }48\)N; longitude: \(05^{\circ }26\)E) is used to validate the developed model. The hourly and the daily solar irradiations are forecasted using the multi input single output and the multi input multi output strategies. Several results are presented to test the feasibility and the performance of the FCWN for forecasting either daily or hourly solar irradiation. Results obtained throughout this paper show that the FCWN is a promising technique for forecasting daily and hourly solar irradiation.
References
Suresh S, Sundararajan N, Savitha R (2013) Supervised learning with complex-valued neural networks. Springer, Berlin
Nitta T (2009) “Complex-valued neural networks: utilizing high-dimensional parameters”, information science reference (an imprint of IGI Global). Hershey, New York
Goh SL, Chen M, Popovic DH, Aihara K, Obradovic D, Mandic DP (2006) Complex-valued forecasting of wind profile. Renew Energy 31:1733–1750
Goh SL, Mandic DP (2005) Nonlinear adaptive prediction of complex-valued signals by complex-valued PRNN. IEEE Trans Signal Process 53(5):1827–1836
Chen S, McLaughlin S, Mulgrew B (1994) Complex-valued radial basis function network, part II: application to digital communications channel equalization. Signal Process 36:175–188
Tripathi BK, Chandra B, Singh M, Kalra PK (2011) Complex generalized-mean neuron model and its applications. Appl Soft Comput 11:768–777
Hirose A (2006) Complex-valued neural networks: distinctive features. In: “Complex-valued neural networks”, studies in computational intelligence (SCI), vol 32. Springer, Berlin, pp 17–41
Hirose A (2006) Complex-valued neural networks fertilize electronics. In: “Complex-valued neural networks”, studies in computational intelligence (SCI), vol 32. Springer, Berlin, pp 3–8
Chairez I, Fuentes R, Poznyak A, Poznyak T (2010) “Robust identification of uncertain Schrödinger type complex partial differential equations” 2010 7th international conference on electrical engineering, computing science and automatic control (CCE 2010), Tuxtla Gutiérrez, Chiapas, México. September 8–10, pp 170–175
Rajendra M, Shankar K (2015) Improved complex-valued radial basis function (ICRBF) neural networks on multiple crack identification. Appl Soft Comput 28:285–300
Hirose A (2011) Nature of complex number and complex-valued neural networks. Front Electr Electron Eng 6(1):171–180 China
Mandic DP, Javidi S, Souretis G, Goh VSL (2007) Why a complex valued solution for a real domain problem. 2007 IEEE workshop on machine learning for signal processing, 27–29 Aug 2007, Thessaloniki, pp 384–389
Hirose A, Yoshida S (2013) Relationship between phase and amplitude generalization errors in complex- and real-valued feed forward neural networks. Neural Comput Appl 22(7–8):1357–1366
Suresh S, Savitha R, Sundararajan N (2011) A fast learning fully complex-valued relaxation network (FCRN). In: Proceedings of international joint conference on neural networks. San Jose, July 31–August 5, 2011
Hirose A (1992) Continuous complex-valued back-propagation learning. Electron Lett 28(20):1854–1855
Li S, Okada T, Chen X, Tang Z (2006) An individual adaptive gain parameter backpropagation algorithm for complex-valued neural networks. In: Wang J et al (ed) Advances in neural networks—ISNN 2006 (Lecture notes in computer science), vol 3971. Springer, Berlin, pp 551–557
Al-Masri AN, Ab Kadir MZA, Hizam H, Mariun N (2015) Simulation of an adaptive artificial neural network for power system security enhancement including control action. Appl Soft Comput 29:1–11
Zhang Y, Li Z, Li K (2011) Complex-valued Zhang neural network for online complex-valued time-varying matrix inversion. Appl Math Comput 217:10066–10073
Zurada JM, Aizenberg I (2008) Fully coupled and feedforward neural networks with complex-valued neurons. In: Advances in intelligent and distributed computing, studies in computational intelligence, vol 78, pp 41–50
Tripathi BK, Kalra PK (2010) High dimensional neural networks and applications. In: Pratihar DK, Jain LC (eds) Intelligent autonomous systems, studies in computational intelligence. Springer, Berlin, pp 215–233
Rattan SP, Hsieh W (2005) Complex-valued neural networks for nonlinear complex principal component analysis. Neural Netw 18:61–69
Yadav A, Mishra D, Ray S, Yadav RN, Kalra PK (2005) Representation of complex-valued neural networks: a real-valued approach. In: Proceedings of 2005 international conference on intelligent sensing and information processing, 4–7 Jan. 2005, pp 331–335
Kuroe Y, Hashimoto N, Mori T (2002) On energy function for complex-valued neural networks and its applications. In: Proceedings of the 9th international conference on neural information processing (ICONIP’ 02), vol 3, 18–22 Nov 2002, pp 1079–1983
Hirose A (1992) Proposal of fully complex-valued neural networks. IEEE international joint conference on neural networks, IJCNN 1992, vol 4, 7–11 Jun 1992, pp 152-157, Baltimore
Kim T, Adali T (2002) Fully complex multi-layer perceptron network for nonlinear signal processing. J VLSI Signal Process 32(1–2):29–43
Li C, Liao X, Yu J (2003) Complex-valued wavelet network. J Comput Syst Sci 67:623–632
Özdemir N, Iskender BB, Özgür NY (2011) Complex valued neural network with Möbius activation function. Commun Nonlinear Sci Numer Simul 16:4698–4703
Wu X, Fan Y (2008) Synchronous generator model identification using half-complex wavelet nonlinear ARX network. International conference on electrical machines and systems, ICEMS 2008, 17–20 Oct 2008, Wuhan, pp 20–25
Mishra S, Sharma A, Panda G (2011) Wind power forecasting model using complex wavelet theory. International conference on energy, automation, and signal (ICEAS), 28–30 Dec 2011, Bhubaneswar, Odisha, pp 1–4
Subramanian K, Savitha R, Suresh S (2014) A complex-valued neuro-fuzzy inference system and its learning mechanism. Neurocomputing 123(10):110–120
Özbay Y, Kara S, Latifoğlu F, Ceylan R, Ceylan M (2007) Complex-valued wavelet artificial neural network for Doppler signals classifying. Artif Intell Med 40:143–156
Saad Saoud L, Rahmoune F, Tourtchine V, Baddari K (2013) Complex-valued forecasting of global solar irradiance. J Renew Sustain Energy 5(4):043124–043145
Mak KL, Peng P, Yiu KFC, Li LK (2013) Multi-dimensional complex-valued Gabor wavelet networks. Math Comput Model 58(11–12):1755–1768
Zainuddin Z, Pauline O (2011) Modified wavelet neural network in function approximation and its application in prediction of time-series pollution data. Appl Soft Comput 11:4866–4874
Babu GS, Suresh S (2013) Meta-cognitive RBF Network and its projection based learning algorithm for classification problems. Appl Soft Comput 13:654–666
Jamil M, Kalam A, Ansari AQ, Rizwan M (2014) Generalized neural network and wavelet transform based approach for fault location estimation of a transmission line. Appl Soft Comput 19:322–332
Rajendra M, Shankar K (2015) Improved complex-valued radial basis function (ICRBF) neural networks on multiple crack identification. Appl Soft Comput 28:285–300
Sivachitra M, Vijayachitra S (2015) A metacognitive fully complex valued functional link network for solving real valued classification problems. Appl Soft Comput 33:328–336
Hu J, Wang J (2012) Global stability of complex-valued recurrent neural networks with time-delays. IEEE Trans Neural Netw Learn Syst 23(6):853–865
Khare A, Rangnekar S (2013) A review of particle swarm optimization and its applications in solar photovoltaic system. Appl Soft Comput 13:2997–3006
Nagia J, Yap KS, Nagi F, Tiong SK, Ahmed SK (2011) A computational intelligence scheme for the prediction of the daily peak load. Appl Soft Comput 11:4773–4788
Seera M, Lim CP, Loo CK, Singh H (2015) A modified fuzzy min-max neural network for data clustering and its application to power quality monitoring. Appl Soft Comput 28:19–29
Venkadesh S, Hoogenboom G, Potter W, McClendon R (2013) A genetic algorithm to refine input data selection for air temperature prediction using artificial neural networks. Appl Soft Comput 13:2253–2260
Zhang W, Wanga J, Wang J, Zhao Z, Tian M (2013) Short-term wind speed forecasting based on a hybrid model. Appl Soft Comput 13:3225–3233
Kulkarni S, Simon SP, Sundareswaran K (2013) A spiking neural network (SNN) forecast engine for short-term electrical load forecasting. Appl Soft Comput 13:3628–3635
Cheng M-Y, Cao M-T (2014) Accurately predicting building energy performance using evolutionary multivariate adaptive regression splines. Appl Soft Comput 22:178–188
Wang J, Zhang W, Li Y, Wang J, Dang Z (2014) Forecasting wind speed using empirical mode decomposition and Elman neural network. Appl Soft Comput 23:452–459
Castro A, Carballo R, Iglesias G, Rabunal JR (2014) Performance of artificial neural networks in nearshore wave power prediction. Appl Soft Comput 23:194–201
Paoli C, Voyant C, Muselli M, Nivet M-L (2009) Solar radiation forecasting using Ad-Hoc time series preprocessing and neural networks. In: Huang D-S et al (eds) Emerging intelligent computing technology and applications (Lecture notes in computer science), vol 5754. Springer, Berlin, pp 898–907
Paoli C, Voyant C, Muselli M, Nivet M-L (2010) Forecasting of preprocessed daily solar radiation time series using neural networks. Solar Energy 84:2146–2160
Martin L, Zarzalejo LF, Polo J, Navarro A, Marchante R, Cony M (2010) Prediction of global solar irradiance based on time series analysis: application to solar thermal power plants energy production planning. Solar Energy 84:1772–1781
Dazhi Y, Jirutitijaroen P, Walsh WM (2012) Hourly solar irradiance time series forecasting using cloud cover index. Solar Energy 86:3531–3543
Mohandes M, Rehman S, Halawani TO (1998) Estimation of global solar radiation using artificial neural networks. Renew Energy 14:179–184
Mohandes M, Balghonaim A, Kassas M, Rehman S, Halawani TO (2000) Use of radial basis functions for estimating monthly mean daily solar radiation. Solar Energy 68:161–168
Mellit A, Benghanem M, Kalogirou SA (2006) An adaptive wavelet-network model for forecasting daily total solar radiation. Appl Energy 83:705–722
Rehman S, Mohandes M (2008) Artificial neural network estimation of global solar radiation using air temperature and relative humidity. Energy Policy 36:571–576
Hontoria L, Aguilera J (2001) Recurrent neural supervised models for generating solar radiation synthetic series. J Intell Robot Syst 31:201–221 Kluwer Academic Publishers
Hontoria L, Aguilera J, Zufiria P (2002) Generation of hourly irradiation synthetic series using the neural network multilayer perceptron. Solar Energy 72:441–446
Hontoria L, Riesco J, Zufiria P, Aguilera J (1999) Improved generation of hourly solar irradiation artificial series using neural networks. In: Proceedings of engineering applications of neural networks, EANN99 Conference,Warsaw, Poland, 13–15 Sept 1999, pp 87–92
Sfetsos A, Coonick AH (2000) Univariate and multivariate forecasting of hourly solar radiation with artificial intelligence techniques. Solar Energy 68:169–178
Lopez G, Batlles FJ, Tovar-Pescador J (2005) Selection of input parameters to model direct solar irradiance by using artificial neural networks. Energy 30:1675–1684
Wang F, Mi Z, Su S, Zhao HS (2012) Short-term solar irradiance forecasting model based on artificial neural network using statistical feature parameters. Energies 5:1355–1370
Hocaoglu FO, Gerek ON, Kurban M (2008) Hourly solar radiation forecasting using optimal coefficient 2-D linear filters and feed-forward neural networks. Solar Energy 82:714–726
Zeng J, Qiao W (2011) Short-term solar power prediction using an RBF neural network. IEEE power and energy society general meeting, 24–29 July 2011, San Diego
Akarslan E, Hocaoglu FO, Edizkan R (2014) A novel M-D (multi-dimensional) linear prediction filter approach for hourly solar radiation forecasting. Energy 73:978–986
Lazzaroni M, Ferrari S, Piuri V, Salman A, Cristaldi L, Faifer M (2015) Models for solar radiation prediction based on different measurement sites. Measurement 63:346–363
Saad Saoud L, Rahmoune F, Tourtchine V, Baddari K (2014) Prediction of the daily global solar irradiation of the great Maghreb region using the complex-valued neural networks. Revue des Energies Renouvelables 17(1):173–185
Saad Saoud L, Rahmoune F, Tourtchine V, Baddari K (2014) Complex-valued wavelet neural network prediction of the daily global solar irradiation of the Great Maghreb Region. 13th international conference on clean energy, June 8–12, 2014, Istanbul, pp 1572–1584
Mihalakakou G, Santamouris M, Asimakopoulos DN (2000) The total solar radiation time series simulation in Athens, using neural networks. Theor Appl Climatol 66:185–197
Boland J (2008) Time series modelling of solar radiation. In: Badescu V (ed) Modeling solar radiation at the earth’s surface. Springer, Berlin, pp 283–312
Tymvios FS, Michaelides SChr, Skouteli CS (2008) Estimation of surface solar radiation with artificial neural networks. In: Badescu V (ed) Modeling solar radiation at the earth’s surface, pp 221–256
Kalogirou SA (2007) Artificial intelligence in energy and renewable energy systems. Nova Science Publishers, New York
Elizondo D, Hoogenboom G, McClendon R (1994) Development of a neural network to predict daily solar radiation. Agric For Meteorol 71:115–132
Kemmoku Y, Orita S, Nakagawa S, Sakakibara T (1999) Daily insolation forecasting using a multistage neural network. Solar Energy 66:193–199
Siqueira AN, Tiba C, Fraidenraich N (2009) Spatial interpolation of daily solar irradiation, through artificial neural networks. In: Proceedings of ISES world congress 2007, vol I–V, pp 2573–2577
Zervas PL, Sarimveis H, Palyvos JA, Markatos NCG (2008) Prediction of daily global solar irradiance on horizontal surfaces based on neural-network techniques. Renew Energy 33:1796–1803
Santamouris M, Mihalakakou G, Psiloglou B, Eftaxias G, Asimakopoulos DN (1999) Modeling the global solar radiation on the earth surface using atmospheric deterministic and intelligent data driven techniques. J Clim 12:3105–3116
Dorvlo A, Jervase JA, Al-Lawati A (2002) Solar radiation estimation using artificial neural networks. Appl Energy 71:307–319
El-Sebaii AA, Al-Hazmi FS, Al-Ghamdi AA, Yaghmour SJ (2010) Global, direct and diffuse solar radiation on horizontal and tilted surfaces in Jeddah, Saudi Arabia. Appl Energy 87:568–576
Chen C, Duan S, Cai Ta, Liu B (2011) Online 24-h solar power forecasting based on weather type classification using artificial neural network. Solar Energy 85:2856–2870
Notton G, Paoli C, Vasileva S, Nivet ML, Canaletti J-L, Cristofari C (2012) Estimation of hourly global solar irradiation on tilted planes from horizontal one using artificial neural networks. Energy 39:166–179
Saad Saoud L, Rahmoune F, Tourtchine V, Baddari K (2014) Short term forecasting of the global solar irradiation using the fuzzy modeling technique: case study of Tamanrasset city, Algeria. In: Proceeding of 13th international conference on clean energy (ICCE-2014), 8–12 June 2014, Istanbul, pp 1585–1590
Winslow JC, Raymond Hunt E Jr, Piper SC (2001) A globally applicable model of daily solar irradiance estimated from air temperature and precipitation data. Ecol Model 143:227–243
Georgiou GM, Koutsougeras C (1992) Complex domain backpropagation. IEEE Trans Circuits Syst II 39:330–334
Kim T, Adali T (2001) Complex backpropagation neural network using elementary transcendental activation functions. In: IEEE Proceedings of the international conference on acoustics, speech, and signal processing, (ICASSP ’01), 07 May 2001–11 May 2001, Salt Lake City, pp 1281–1284
Huang S-C (2011) Forecasting stock indices with wavelet domain kernel partial least square regressions. Appl Soft Comput 11:5433–5443
Banakar A, Azeem MF (2008) Artificial wavelet neural network and its application in neuro-fuzzy models. Appl Soft Comput 8:1463–1485
Biswal B, Dash PK, Panigrahi BK, Reddy JBV (2009) Power signal classification using dynamic wavelet network. Appl Soft Comput 9:118–125
Zainuddin Z, Pauline Ong (2011) Modified wavelet neural network in function approximation and its application in prediction of time-series pollution data. Appl Soft Comput 11:4866–4874
Banakar A, Azeem MF (2012) Local recurrent sigmoidal-wavelet neurons in feed-forward neural network for forecasting of dynamic systems: Theory. Appl Soft Comput 12:1187–1200
Hsu CF (2013) A self-evolving functional-linked wavelet neural network for control applications. Appl Soft Comput 13:4392–4402
Tofighi M, Alizadeh M, Ganjefar S, Alizadeh M (2015) Direct adaptive power system stabilizer design using fuzzy wavelet neural network with self-recurrent consequent part. Appl Soft Comput 28:514–526
Dehghan SAM, Danesh M, Sheikholeslam F, Zekri M (2015) Adaptive force-environment estimator for manipulators based on adaptive wavelet neural network. Appl Soft Comput 28:527–540
Chuang LZH, Wu LC, Doong DJ, Kao CC (2008) Two-dimensional continuous wavelet transform of simulated spatial images of waves on a slowly varying topography. Ocean Eng 35:1039–1051
Hirose A (1992) Continuous complex-valued backpropagation learning. Electron Lett 28(20):1854–1855
Benvenuto N, Piazza F (1992) On the complex backpropagation algorithm. IEEE Trans Signal Process 40:967–969
Nitta T (1997) An extension of the back-propagation algorithm to complex numbers. Neural Netw 10(8):1391–1415
Hanna AI, Mandic DP (2003) A fully adaptive normalized nonlinear gradient descent algorithm for complex-valued nonlinear adaptive filters. IEEE Trans Signal Process 51(10):2540–2549
Zimmermann HG, Minin A, Kusherbaeva V (2011) Comparison of the complex valued and real valued neural networks trained with gradient descent and random search algorithms. In: ESANN 2011 proceedings, European symposium on artificial neural networks, computational intelligence and machine learning. Bruges (Belgium) 27–29 April 2011, pp 213–218
Ramaswamy S, Suresh S, Sundararajan N (2009) A fully complex-valued radial basis function network and its learning algorithm. Int J Neural Syst 19(04):253–267
Murphy AH (1988) Skill scores based on the mean square error and their relationships to the correlation coefficient. Mon Weather Rev 116:2417–2424
Sideratos G, Hatziargyriou ND (2007) An advanced statistical method for wind power forecasting. IEEE Trans Power Syst 22(1):258–265
Lipperheide M, Bosch JL, Kleissl J (2015) Embedded nowcasting method using cloud speed persistence for a photovoltaic power plant. Solar Energy 112:232–238
Nielsen TS, Joensen A, Madsen H, Landberg L, Giebel G (1998) A new reference for wind power forecasting. Wind Energy 1:29–34
Acknowledgments
The first author thanks Professors G. Osmanov and A. Abassov for their comments to develop the proofs in the appendix. We thank the department’s head of database in the national office of meteorology (ONM) of Algeria for providing the real dataset used throughout this paper. This work is supported by ‘the National Committee for Evaluation and Planning Unit of University Research, Ministry of Higher Education and Scientific Research, Algeria’ under project number: A10N01UN350120130013.
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
\(f\left( z\right) \) proposed in this paper is a complex valued wavelet function. This one is a valid function for the complex valued network if it satisfied the five conditions cited before in the current paper and is should be admissible (Eqs. (2)–(5)) to be acceptable like wavelet function.
Proof
Let us take: \(f\left( z\right) =u(x,y)+jv(x,y)\)
It could prove that it is nonlinear for all \(z\in C\), and the its real and imaginary parts are nonlinear and bounded for all \(\hbox {x},y\in R\).
\(f\left( z\right) \) is not constant, so it not entire.
\(u\left( {x,y}\right) \) and \(v\left( {x,y}\right) \) should be bounded, therefore \(f\left( z\right) \) is bounded.
The partial derivatives \(\frac{\partial u}{\partial x}\), \(\frac{\partial u}{\partial y}\), \(\frac{\partial v}{\partial x}\), and \(\frac{\partial v}{\partial y}\) exist, and they are given as follows:
Decomposing the wavelet function into real and imaginary parts, one can find:
\(u(x,y)=\frac{\alpha _1 \beta _1 +\alpha _2 \beta _2 }{\beta _1^2 +\beta _2^2 }\) and \(v(x,y)=\frac{\alpha _2 \beta _1 -\hbox {}\alpha _1 \beta _2 }{\beta _1^2 +\beta _2^2 }\)
where
One can remark from Eqs. (28)–(31) that:
Using some algebra, we can find that: \(\frac{\partial u(x,y)}{\partial x}=\frac{\partial v(x,y)}{\partial y}\).
Using the same method, the relations of the two other partial derivatives \(\frac{\partial u(x,y)}{\partial y}\) and \(\frac{\partial v(x,y)}{\partial x}\) could be identified like: \(\frac{\partial u(x,y)}{\partial y}=-\frac{\partial v(x,y)}{\partial x}\)
They are continuous and bounded because they satisfy the two relations \(\frac{\partial u}{\partial x}\frac{\partial v}{\partial y}\ne \frac{\partial u}{\partial y}\frac{\partial v}{\partial x}\) except if \(\frac{\partial u}{\partial x}=\frac{\partial v}{\partial x}=0\) and \(\frac{\partial u}{\partial y}=\frac{\partial v}{\partial y}=0\), because:
So the function proposed in this paper could be used as fully activation function.
As proved before throughout this paper (Eqs. (2)– (5)) that it is an admissible function, therefore, the function could be used as wavelet activation function.
Rights and permissions
About this article
Cite this article
Saad Saoud, L., Rahmoune, F., Tourtchine, V. et al. Fully Complex Valued Wavelet Network for Forecasting the Global Solar Irradiation. Neural Process Lett 45, 475–505 (2017). https://doi.org/10.1007/s11063-016-9537-7
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-016-9537-7