Optimizing Solar Radiation Prediction Based on The Internet of Things Platform in Photovoltaic Power Plant

Subject Areas : IOT

Neda Ashrafi Khozani ¹ , Maryam Mahmoudi ² , Shabnam Nasr Esfahani ³

1 - Department of Computer Engineering, Meymeh Branch, Islamic Azad University, Meymeh, Iran
2 - Department of Computer Engineering, Meymeh Branch, Islamic Azad University, Meymeh, Iran
3 - Department of Electrical Engineering, Meymeh Branch, Islamic Azad University, Meymeh, Iran

Received: 2023-09-16 Accepted : 2023-12-22 Published : 2024-07-20

Keywords: Internet of Things, Decision Tree, Machine Learning, Bat Algorithm, Photovoltaic Power Plants.,

Abstract :

The solar radiation value parameter is one of the most important parameters in determining the output power value of photovoltaic panels. Accurate prediction of this parameter is crucial for dispatching and load management planning. Managers and designers encounter economic and managerial challenges due to the uncertainty and difficulty in predicting solar radiation levels. This research introduces a highly accurate prediction method utilizing tree-based methods, enhanced by meta-heuristic algorithms to boost performance. The proposed method emphasizes preventing overfitting and ensuring high reliability for use in Internet of Things systems. Meta-heuristic algorithms are utilized for optimizing tree-based methods, as well as for feature and instance selection. Employing meta-heuristic methods as the main innovation in this research not only optimizes machine learning model settings but also mitigates the impact of noise, outliers, and ineffective inputs, thereby enhancing the final output quality. Utilizing an innovative fitness function in model optimization enhances prediction accuracy and adaptability to real photovoltaic power plant environments. The final outcome is a strong model that has a score of 0.95 with the R-square criterion and is optimal model.

highlight:

Accurate prediction of the amount of solar radiation as an important parameter in determining the amount of output power of photovoltaic panels.

Optimization of tree-based models by meta-heuristic algorithms for modeling the amount of solar radiation parameter.

Maintaining the balance between the accuracy of the model and its simplicity and ability to be implemented in Internet of Things devices has been optimized.

In the end, a strong model that has a score of 0.95 with the R-square criterion was obtained in this research.

The final model can be implemented in the environment of power plants based on the Internet of Things.

References:

[1] N. M. Kumar, K. Atluri and S. Palaparthi, “Internet of Things (IoT) in Photovoltaic Systems,” National Power Engineering Conference (NPEC), 2018, pp. 1-4, doi: 10.1109/NPEC.2018.8476807.
[2] A. Mellit, M. Menghanem and M. Bendekhis, “Artificial neural network model for prediction solar radiation data: application for sizing stand-alone photovoltaic power system,” IEEE Power Engineering Society General Meeting, 2005, San Francisco, CA, USA, 2005, pp. 40-44 Vol. 1, doi: 10.1109/PES.2005.1489526.
[3] A. Angstrom, “Solar and terrestrial radiation: Report to the international commission for solar research on actinometric investigations of solar and atmospheric radiation,” Quarterly Journal of the Royal Meteorological Society, 1924, pp. 121-126,1924, doi:10.1002/qj.49705021008.
[4] J. Prescott, “Evaporation from a water surface in relation to solar radiation,” Transactions of the Royal Society of South Australia, vol. 64, pp 114-118, 1940, doi: 10.4236/epe.2017.912045.
[5] A. A. Trabea and M.M. Shaltout, “Correlation of global solar radiation with meteorological parameters over Egypt,” Renewable Energy, vol. 21, pp. 297-308, Oct. 2000, doi:10.1016/S0960-1481(99)00127-5.
[6] D.Yeboah-Amankwah and K.Agyeman, “Differential Ångstrom model for predicting insolation from hours of sunshine,” Solar Energy, vol. 45, pp. 371-377, 1990, doi:10.1016/0038-092X(90)90158-9.
[7] H. Ninomiya, “Study on application of amedas meteorological data to the simulation of building heat environment,” University of Tokyo, 1994.
[8] J. C . Cao and S. H. Cao, “Study of forecasting solar irradiance using neural networks with preprocessing sample data by wavelet analysis,” Energy, vol. 31, pp. 3435-3445, Dec. 2006, doi: 10.1016/j.energy.2006.04.001.
[9] X. Qing and Y. Niu, “Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM,” Energy, vol. 148, pp. 461-468, Apr. 2018, doi: 10.1016/j.energy.2018.01.177.
[10] D. Pothineni, M. R. Oswald, J. Poland and M. Pollefeys,“KloudNet: Deep Learning for Sky Image Analysis and Irradiance Forecasting,” German Conference on Pattern Recognition, 2018, pp. 535-551, doi:10.1007/978-3-030-12939-2_37.
[11] J. Lago, K. D. Brabandere, F. D. Ridder and B. D. Schuttera, “Short-term forecasting of solar irradiance without local telemetry: A generalized model using satellite data,” SolarEnergy, vol. 173, pp. 566-577, Oct. 2018, doi: 10.1016/j.solener.2018.07.050.
[12] N. Dong, J. F. Chang, A. G. Wu and Z. K. Gao, “A novel convolutional neural network framework based solar irradiance prediction method,” International Journal of Electrical Power & Energy Systems, vol. 114, pp. 1-19, Jan. 2020, doi: 10.1016/j.ijepes.2019.105411.
[13] N. Sharma, P. Sharma, D. Irwin and P. Shenoy, “Predicting solar generation from weather forecasts using machine learning,” IEEE International Conference on Smart Grid Communications (SmartGridComm), 2011, pp. 528-533, doi: 10.1109/SmartGridComm.2011.6102379.
[14] P. J. M. Ali and R. H. Faraj, “Data normalization and standardization: a technical report,” Mach. Learn. Tech. Rep., vol. 1, no. 1, pp. 1-6, 2014, doi: 10.13140/RG.2.2.28948.04489.
[15] Y.-Y. Song and L. Ying, “Decision tree methods: applications for classification and prediction,” Shanghai archives of psychiatry, vol. 27, no. 2, pp. 130-135, Apr. 2015, doi: 10.11919/j.issn.1002-0829.215044.
[16] N. Bhargava, G. Sharma, R. Bhargava and M. Mathuria, “Decision tree analysis on j48 algorithm for data mining,” Intrenational Journal of Advanced Research in Computer Science and Software Engineering, vol. 3, no. 6, 2013.
[17] D. Borup, B.J. Christensen, N.S. Mühlbach and M.S. Nielsen, “Targeting predictors in random forest regression,” International Journal of Forecasting, vol. 39, pp. 841–868, 2023, doi:10.1016/j.ijforecast.2022.02.010.
[18] Y. Li et al., “Random forest regression for online capacity estimation of lithium-ion batteries,” Applied energy, vol. 232, pp. 197-210, Dec. 2018, doi: 10.1016/j.apenergy.2018.09.182.
[19] R. Seyghaly, J. Garcia, X. Masip-Bruin and M. M. Varnamkhasti, “Interference Recognition for Fog Enabled IoT Architecture using a Novel Tree-based Method,” IEEE International Conference on Omni-layer Intelligent Systems (COINS), 2022, pp. 1-6, doi: 10.1109/COINS54846.2022.9854944.
[20] G. Sembina, “Building a scoring model using the ADABOOST ensemble model,” International Conference on Smart Information Systems and Technologies (SIST), 2022, doi:10.1109/sist54437.2022.9945713.
[21] D. P. Solomatine and D. L. Shrestha, “AdaBoost.RT: a boosting algorithm for regression problems,” IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541), Budapest, Hungary, 2004, pp. 1163-1168 vol.2, doi: 10.1109/IJCNN.2004.1380102.
[22] X. S. Yang, “A New Metaheuristic Bat-Inspired Algorithm,” Nature Inspired Cooperative Strategies for Optimization (NICSO 2010), vol. 284, pp. 65–74, 2010, doi: 10.1007/978-3-642-12538-6_6.
[23] M.Banerjee, “Cook's distance in linear longitudinal models,” Communications in Statistics-Theory and Methods, vol. 27, pp. 2973-2983, 1998, doi: 10.1080/03610929808832267.
[24] J. Carmona, I. Lopez, J. Mateo, L. Jimenez and E. Aldana, “A distance-based method for outlier detection on high dimensional datasets,” IEEE Latin America Transactions, vol. 18, pp. 589–597, 2020, doi:10.1109/tla.2020.9082731.
[25] E. -S. M. El-Kenawy et al., “Advanced Ensemble Model for Solar Radiation Forecasting Using Sine Cosine Algorithm and Newton’s Laws,” in IEEE Access, vol. 9, pp. 115750-115765, 2021, doi: 10.1109/ACCESS.2021.3106233.