Applying artificial neural network techniques to forecast the electricity production of photovoltaic (PV) power plants is a novel concept. A reliable analytical model for calculating the energy output of a grid-connected solar plant is very difficult to establish because of hourly, daily, and seasonal variations in climate. The current study estimated and predicted the energy production of a connected PV system that was installed in Cairo, Egypt (30.13° N and 31.40 ° E) using an artificial neural network. Four seasons' worth of data (summer, autumn, winter, and spring) were methodically assessed using information from the climate database. The parameters that had an impact on the electrical data of PV modules included meteorological and irradiation variables, energy output, and the user's needs used to verify the NARX feedback neural networks. Prediction performance metrics were obtained, such as the correlation coefficient (R) and root mean square error (RMSE). The observed correlation coefficient ranged from 99% to 100%, indicating that the expected results are verified, while the mean error fluctuates very little.
Citation: Marwa M. Ibrahim, Amr A. Elfeky, Amal El Berry. Forecasting energy production of a PV system connected by using NARX neural network model[J]. AIMS Energy, 2024, 12(5): 968-983. doi: 10.3934/energy.2024045
Applying artificial neural network techniques to forecast the electricity production of photovoltaic (PV) power plants is a novel concept. A reliable analytical model for calculating the energy output of a grid-connected solar plant is very difficult to establish because of hourly, daily, and seasonal variations in climate. The current study estimated and predicted the energy production of a connected PV system that was installed in Cairo, Egypt (30.13° N and 31.40 ° E) using an artificial neural network. Four seasons' worth of data (summer, autumn, winter, and spring) were methodically assessed using information from the climate database. The parameters that had an impact on the electrical data of PV modules included meteorological and irradiation variables, energy output, and the user's needs used to verify the NARX feedback neural networks. Prediction performance metrics were obtained, such as the correlation coefficient (R) and root mean square error (RMSE). The observed correlation coefficient ranged from 99% to 100%, indicating that the expected results are verified, while the mean error fluctuates very little.
[1] | Abo-Khalil AG, Sayed K, Radwan A, et al. (2023) Analysis of the PV system sizing and economic feasibility study in a grid-connected PV system. Case Studies Thermal Eng 45: 102903. https://doi.org/10.1016/j.csite.2023.102903 doi: 10.1016/j.csite.2023.102903 |
[2] | Satpathy R, Pamuru V (2021) Chapter 9—Grid-connected solar PV power systems. Sol PV Power, 365–433. https://doi.org/10.1016/B978-0-12-817626-9.00009-5 doi: 10.1016/B978-0-12-817626-9.00009-5 |
[3] | Qazi S (2017) Chapter 5—Fixed standalone PV systems for disaster relief and remote areas. Standalone Photovoltaic (PV) Syst Disaster Relief Remote Areas, 139–175. https://doi.org/10.1016/B978-0-12-803022-6.00005-8 doi: 10.1016/B978-0-12-803022-6.00005-8 |
[4] | Huang P, Lovati M, Zhang XX, et al. (2019) Transforming a residential building cluster into electricity prosumers in Sweden: Optimal design of a coupled PV-heat pump-thermal storage-electric vehicle system. Appl Energy 255: 113864. https://doi.org/10.1016/j.apenergy.2019.113864. doi: 10.1016/j.apenergy.2019.113864 |
[5] | Boscaino V, Ditta V, Marsala G, et al. (2024) Grid-connected photovoltaic inverters: Grid codes, topologies and control techniques. Renewable Sustainable Energy Rev 189: 113903. https://doi.org/10.1016/j.rser.2023.113903 doi: 10.1016/j.rser.2023.113903 |
[6] | Numbi B, Malinga S (2017) Optimal energy cost and economic analysis of a residential grid-interactive solar PV system-case of eThekwini municipality in South Africa. Appl Energy 186: 28–45. https://doi.org/10.1016/j.apenergy.2016.10.048 doi: 10.1016/j.apenergy.2016.10.048 |
[7] | Guliyev M, Rustamova S, Makhmudova V (2023) The modern status and prospects for further development in the Australian energy sector: Transformation, external economic relations, investment climate. Energy Policy J 26: 47–64. https://doi.org/10.33223/epj/166436 doi: 10.33223/epj/166436 |
[8] | Nakach I, Mouhat O, Shamass R, et al. (2023) Review of strategies for sustainable energy in Morocco. Energy Policy J 26: 65–104. https://doi.org/10.33223/epj/163373 doi: 10.33223/epj/163373 |
[9] | Olabi AG, Abdelkareem MA, Semeraro C, et al. (2023) Artificial neural networks applications in partially shaded PV systems. Thermal Sci Eng Progress 37: 101612. https://doi.org/10.1016/j.tsep.2022.101612 doi: 10.1016/j.tsep.2022.101612 |
[10] | Al-Othman A, Tawalbeh M, Martis R, et al. (2022) Artificial intelligence and numerical models in hybrid renewable energy systems with fuel cells: Advances and prospects. Energy Convers Manage 253: 115154. https://doi.org/10.1016/j.enconman.2021.115154 doi: 10.1016/j.enconman.2021.115154 |
[11] | Elsheikh A, Sharshir S, Abd Elaziz M, et al. (2019) Modeling of solar energy systems using artificial neural network: A comprehensive review. Sol Energy 180: 622–39. https://doi.org/10.1016/j.solener.2019.01.037 doi: 10.1016/j.solener.2019.01.037 |
[12] | Moreira M, Balestrassi P, Paiva A, et al. (2021) Design of experiments using artificial neural network ensemble for photovoltaic generation forecasting. Renewable Sustainable Energy Rev 135: 110450. https://doi.org/10.1016/j.rser.2020.110450 doi: 10.1016/j.rser.2020.110450 |
[13] | Ledmaoui Y, El Fahli A, Chehri A, et al. (2023) Monitoring solar energy production based on internet of things with artificial neural networks forecasting. Proc Comput Sci 225: 88–97. https://doi.org/10.1016/j.procs.2023.09.095 doi: 10.1016/j.procs.2023.09.095 |
[14] | Liu R, Chen T, Sun G, et al. (2022) Short-term probabilistic building load forecasting based on feature integrated artificial intelligent approach. Electr Power Syst Res 206: 107802. https://doi.org/10.1016/j.epsr.2022.107802 doi: 10.1016/j.epsr.2022.107802 |
[15] | Xu L, Hu MM, Fan C (2022) Probabilistic electrical load forecasting for buildings using Bayesian deep neural networks. J Build Eng 46: 103853. https://doi.org/10.1016/j.jobe.2021.103853 doi: 10.1016/j.jobe.2021.103853 |
[16] | Chaouki G, Al-Mufti OAA, Al-Isawi OAM, et al. (2022) Short-term building electrical load forecasting using adaptive neuro-fuzzy inference system (ANFIS). J Build Eng 52: 104323. https://doi.org/10.1016/j.jobe.2022.104323 doi: 10.1016/j.jobe.2022.104323 |
[17] | Irshad A, Nqibullah K, Elkholy M, et al. (2024) Techno-economic evaluation and comparison of the optimal PV/wind and grid hybrid system with horizontal and vertical axis wind turbines. Energy Convers Manage: X 23: 100638. https://doi.org/10.1016/j.ecmx.2024.100638 doi: 10.1016/j.ecmx.2024.100638 |
[18] | Irshad A, Ludin G, Ludin S, et al. (2024) Integration and performance analysis of optimal large-scale hybrid PV and pump hydro storage system based upon floating PV for practical application. Energy Convers Manage: X 22: 100599. https://doi.org/10.1016/j.ecmx.2024.100599 doi: 10.1016/j.ecmx.2024.100599 |
[19] | Nkuryngoma O, Seljuk SB (2021) Solar power plant generation forecasting using NARX neural network model: A case study. Int J Energy Appl Technol 8: 80–92. https://doi.org/10.31593/ijeat.870088 doi: 10.31593/ijeat.870088 |
[20] | Jiménez-Castillo G, Muñoz-Rodríguez FJ, Martinez-Calahorro AJ, et al. (2020) Impacts of array orientation and tilt angles for photovoltaic self-sufficiency and self-consumption indices in olive mills in Spain. Electronics 9: 348. https://doi.org/10.3390/electronics9020348 doi: 10.3390/electronics9020348 |
[21] | Rahman MM, Shakeri M, Tiong SK, et al. (2021) Prospective methodologies in hybrid renewable energy systems for energy prediction using artificial neural networks. Sustainability 13: 2393. https://doi.org/10.3390/su13042393 doi: 10.3390/su13042393 |
[22] | Liu Q, Chen W, Huo H, et al. (2020) An optimal NARX neural network identification model for a magnetorheological damper with force-distortion behavior. Front Mater 7: 10. https://doi.org/10.3389/fmats.2020.00010 doi: 10.3389/fmats.2020.00010 |
[23] | Menezes JMP, Barreto GA (2008) Long-term time series prediction with the NARX network: An empirical evaluation. Neurocomputing 71: 3335–3343. https://doi.org/10.1016/j.neucom.2008.01.030 doi: 10.1016/j.neucom.2008.01.030 |
[24] | Berggren JL, Folkerts M, Knorr WR, et al. (2024) Mathematics: References & edit history. Encyclopedia Britannica. Available from: https://www.britannica.com/science/mathematics. |
[25] | Haykin S (1998) Neural networks: A comprehensive foundation. 2nd edition, Prentice Hall, PTR Upper Saddle River, NJ, USA. Available from: https://dl.acm.org/doi/book/10.5555/521706. |