Prediction and modeling of harmonic current behavior in grid-connected photovoltaic systems based on NARX networks

  • A.A. Jumilla-Corral
  • C. Pérez-Tello
  • H.E. Campbell-Ramírez
  • Z.Y. Medrano-Hurtado Instituto Tecnologico de Mexicali
  • P. Mayorga-Ortiz
Keywords: model, prediction, inverters, photovoltaic systems, artificial neural networks, nonlinear autoregressive with external input


This research presents the modeling and prediction of the harmonic behavior of current in an electric power supply grid with integration of photovoltaic power by inverters. The methodology used was based on the use of recurrent artificial neural networks of the nonlinear autoregressive with external input type. Work data was obtained from experimental sources through the use of a test bench, measurement, acquisition and monitoring equipment. The input-output parameters for the neural network were the current values in the inverter and in the supply grid respectively. The results showed that the neural network can capture the dynamics of the analyzed system. The generated model presented flexibility in data handling, allowing to represent and predict the behavior of the harmonic phenomenon. The obtained algorithm can be transferred to physical or virtual systems for the control or reduction of harmonic distortion.


Javaid, N., Hafeez, G., Iqbal, S., Alrajeh, N., Alabed, M.S. and Guizani, M. Energy Efficient Integration of Renewable Energy Sources in the Smart Grid for Demand Side Management. IEEE Access, 6, pp. 77077-77096, 2018. DOI: 10.1109/ACCESS.2018.2866461

Gómez, M.D., Hernández, I.A., López, J., González, G. and Beristain, R. Industrial wastewater treatment by anaerobic digestion using a solar heater as renewable energy for temperature-control. Revista Mexicana de Ingeniería Química, 19(1), pp. 9-16, 2020. DOI: 10.24275/RMIQ/IA1853

Álvarez, C., Santana, G., Viveros, T. and Barrera, E. Efecto de los parámetros de depósito de silicio polimorfo por técnica PECVD sobre las propiedades químicas, nano-estructurales, optoelectrónicas y de foto-degradación. Revista Mexicana de Ingeniería Química, 16(3), pp. 991-1001, 2019.


Reinders, A., Debije, M. G. and Rosemann, A. Measured Efficiency of a Luminescent Solar Concentrator PV Module Called Leaf Roof. IEEE Journal of Photovoltaics, 7(6), pp. 1663-1666, 2017. DOI: 10.1109/JPHOTOV.2017.2751513

Singh, S., Kewat, S., Singh, B., Panigrahi B. K. and Kushwaha, M. K. Seamless Control of Solar PV Grid Interfaced System with Islanding Operation. IEEE Power and Energy Technology Systems Journal, 6(3), pp. 162-171, 2019. DOI: 10.1109/JPETS.2019.2929300

Gupta, A-K., Pawar, V., Joshi, M. S., Agarwal V. and Chandran, D. A Solar PV Retrofit Solution for Residential Battery Inverters. IEEE 44th Photovoltaic Specialist Conference (PVSC), Washington, DC, USA, 2017, pp. 2986-2990. DOI: 10.1109/PVSC.2017.8366082

Bincy, K-J. Grid integration of PV systems-issues and requirements. IEEE International Conference on Circuits and Systems (ICCS), Thiruvananthapuram, India, 2017, pp. 215-219. DOI: 10.1109/ICCS1.2017.8325993

Plangklang, B., Thanomsat, N. and Phuksamak, T. A verification analysis of power quality and energy yield of a large-scale PV rooftop. Energy Reports, 2, pp. 1-7, 2016. DOI: 10.1016/j.egyr.2015.12.002

Liu, Y., Rau, S., Wu, C., and Lee, W. Improvement of Power Quality by Using Advanced Reactive Power Compensation. IEEE Transactions on Industry Applications, 54(1), pp. 18-24, 2018. DOI: 10.1109/TIA.2017.2740840

Sangwongwanich A. and Blaabjerg, F. Mitigation of Interharmonics in PV Systems with Maximum Power Point Tracking Modification. IEEE Transactions on Power Electronics, 34(9), pp. 8279-8282, 2019. DOI: 10.1109/TPEL.2019.2902880

Nduka, O-S. and Pal, B-C. Harmonic characterization model of grid interactive photovoltaic systems. IEEE International Conference on Power System Technology (POWERCON), Wollongong, NSW, Australia, 2016, pp. 1-6.DOI: 10.1109/POWERCON.2016.7753863

Vargas, U., Ramirez, A., and Lazaroiu, G-C. Flexible harmonic domain model of a photovoltaic system for steady-state analysis. International Conference on Energy and Environment (CIEM), Bucharest, Romania, 2017, pp. 311-315. DOI: 10.1109/CIEM.2017.8120805

Deng, Z., Rotaru, M-D, and Sykulski, J-K. Harmonic Analysis of LV distribution networks with high penetration PV. International Conference on Modern Power Systems (MPS), Cluj-Napoca, Romania, 2017, pp. 1-6. DOI: 10.1109/MPS.2017.7974392

Todeschini, G., Balasubramaniam, S. and Petar Igic (2019). Time-Domain Modeling of a Distribution System to Predict Harmonic Interaction Between PV Converters. IEEE Transactions on Sustainable Energy, 10(3), pp. 1450-1458, 2019. DOI: 10.1109/TSTE.2019.2901192

Mubarok, A-F., Octavira, T., Sudiharto, I., Wahjono, E., and Anggriawan, D-O. Identification of harmonic loads using fast fourier transform and radial basis Function Neural Network. International Electronics Symposium on Engineering Technology and Applications (IES-ETA), Surabaya, Indonesia, 2017, pp.198-202. DOI: 10.1109/ELECSYM.2017.8240402

Mejia, A., Amezquita, J-P., Dominguez, A., Valtierra, M., Razo, J-R. and Granados, D. A scheme based on PMU data for power quality disturbances monitoring. IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society, Beijing, China, 2017, pp. 3270-3275, DOI: 10.1109/IECON.2017.8216553

Rodriguez, M-A., Sotomonte, J-F., Cifuentes J. and Bueno, M. Classification of Power Quality Disturbances using Hilbert Huang Transform and a Multilayer Perceptron Neural Network Model. International Conference on Smart Energy Systems and Technologies (SEST), Porto, Portugal, 2019, pp. 1-6. DOI: 10.1109/SEST.2019.8849114

Kumar, N., Singh, B. and Panigrahi, B-K. Framework of Gradient Descent Least Squares Regression-Based NN Structure for Power Quality Improvement in PV-Integrated Low-Voltage Weak Grid System. IEEE Transactions on Industrial Electronics, 66(12), pp. 9724-9733, 2019. DOI: 10.1109/TIE.2018.2886765

Shukl, P. and Singh, B. Delta-Bar-Delta Neural-Network-Based Control Approach for Power Quality Improvement of Solar-PV-Interfaced Distribution System. IEEE Transactions on Industrial Informatics, 16(2), pp. 790-801, 2020. DOI: 10.1109/TII.2019.2923567

Hatata, A-Y. and Eladawy, M. Prediction of the true harmonic current contribution of nonlinear loads using NARX neural network. Alexandria Engineering Journal, 57(3), pp.1509-1518, 2017. DOI: 10.1016/j.aej.2017.03.050

Panoiu, M., Panoiu, C. and Ghiormez, L. Neuro-fuzzy modeling and prediction of current total harmonic distortion for high power nonlinear loads. Innovations in Intelligent Systems and Applications (INISTA), Thessaloniki, Greece, 2018, pp. 1-7. DOI: 10.1109/INISTA.2018.8466290

Alhroob, E., Mohammed, M-F., Lim, C-P. and Tao, H. A Critical Review on Selected Fuzzy Min-Max Neural Networks and Their Significance and Challenges in Pattern Classification. IEEE Access, 7, pp. 56129-56146, 2019. DOI: 10.1109/ACCESS.2019.2911955

Shrestha, A. and Mahmood, A. Review of Deep Learning Algorithms and Architectures. IEEE Access, 7, pp. 53040-53065, 2019. DOI: 10.1109/ACCESS.2019.2912200

Rezk, N-M., Purnaprajna, M., Nordstrom, T. and Ul-Abdin, Z. Recurrent Neural Networks: An Embedded Computing Perspective. IEEE Access, 8, pp. 57967-57996, 2020. DOI: 10.1109/ACCESS.2020.2982416

Xia, W., Zhu, W., Liao, B., Chen, M., Cai, L. and Huang, L. Novel architecture for long short-term memory used in question classification. Neurocomputing, 299, pp. 20-31, 2018. DOI: 10.1016/j.neucom.2018.03.020

Salas, J., by Barros, F. and Martinez, F. Deep Learning: Current State. IEEE Latin America Transactions, 17(12), pp. 1925-1945, 2019. DOI: 10.1109/TLA.2019.9011537

Li, Y. and Cao, H. Prediction for Tourism Flow based on LSTM Neural Network. Proceedings Computer Science, 129, pp. 277-283, 2018. DOI: 10.1016/j.procs.2018.03.076

Cortez, B., Carrera, B., Young-Jin, K. and Jae-Yoon, J. An architecture for emergency event prediction using LSTM recurrent neural networks. Expert Systems with Applications, 97, pp. 315-324, 2018. DOI: 10.1016/j.eswa.2017.12.037

Liu, F., Chen, Z. and Wang, J. Video image target monitoring based on RNNLSTM. Multimedia Tools and Applications, 78, pp. 4527-4544, 2018. DOI: 10.1007/s11042-018-6058-6

Hudson M., Hagan, M., and Demuth, H. Matlab Deep Learning Toolbox User's Guide. MATHWORKS, 2019.

Figueroa, E., Farías, V.S., Segura, M., Andrade, I., Monter, M.I. and Chávez, A.M. Using artificial neural networks in prediction of the drying process of foods that are rich in sugars. Revista Mexicana de Ingeniería Química, 20(1), pp. 161-171, 2020. DOI: 10.24275/RMIQ/SIM1403

Díaz, L., Hidalgo, C.A., Santoyo, E. and Hermosillo, J. Evaluación de técnicas de entrenamiento de redes neuronales para estudios geotermométricos de sistemas geotérmicos. Revista Mexicana de Ingeniería Química, 12(1), pp. 105-120, 2020.

How to Cite
Jumilla-Corral, A., Pérez-Tello, C., Campbell-Ramírez, H., Medrano-Hurtado, Z., & Mayorga-Ortiz, P. (2021). Prediction and modeling of harmonic current behavior in grid-connected photovoltaic systems based on NARX networks. Revista Mexicana De Ingeniería Química, 20(3), Sim2453.
Simulation and control