Document Type : Original Article
Authors
1 Department of Electrical Engineering Polytechnic School of Abomey-Calavi (EPAC), Abomey-Calavi, Benin.
2 Department of ENSET-Lokossa National University of Science, Technology, Engineering and Mathematics of Abomey (UNSTIM), Abomey, Benin
Abstract
In this work, the photovoltaic power forecast for the next 24 hours by combining a time series forecasting model (LSTM) and a regression model (XGBoost) from direct irradiation only is performed. Several meteorological parameters such as irradiance, ambient temperature, wind speed, relative humidity, sun position, dew point were identified as influencing parameters of PV power variability. Thanks to the parameter extraction and selection techniques of the XGBoost model, only the direct irradiation could be kept as input parameters. The LSTM model was used to predict the direct irradiation for the next 24 hours and the XGBoost model to estimate the future power from the predicted irradiation. These models were developed under Python 3, the exploited data were downloaded in the PVGIS database for the city of Abomey-Calavi in Benin and the prediction was carried out on a panel of 1000W of peak power. An experimental validation was then performed by comparing the predicted irradiance values to the measured values on site. It was obtained for the LSTM model a root mean square error of 3.66 W/m2 and for the XGBoost model a root mean square error and a regression coefficient of 1.72 W and 0.992129 respectively. These results were compared to the LSTM-XGBoost performances with irradiation, temperature, sun position and wind speed as inputs. It was found that the use of irradiation alone as input did not as such impair the forecast performance. The proposed method was also found to be more efficient than LSTM and CNN models used alone.
Keywords
Main Subjects
[1] IEA, “Africa Energy Outlook 2019 – Analysis,” IEA. https://www.iea.org/reports/africa-energy-outlook-2019 (accessed Feb. 07, 2022).
[2] IRENA, GIZ, and KFW, “La transition vers les énergies renouvelables en Afrique : Renforcer l’accès, la résilience et la prospérité,” 2021. [Online]. Available: https://www.irena.org/-/media/Files/IRENA/Agency/Publication/2013/Afrique_nergies_renouvelables.pdf
[3] D. Grand, A. Latrobe, C. Le Brun, and R. Vidil, “La transition énergétique sous contrainte de gestion de l’intermittence des énergies renouvelables”.
[4] A. FOPAH-LELE, “Technologie de stockage d’énergie pour les infrastructures énergétiques en Afrique subsaharienne: L’hydrogène comme perspective!,” Énerg. DURABLE EN Afr. Initiat., p. 68.
[5] C. Glaize, “Energies renouvelables et gestion du stockage de l’énergie: une necessité? Etat actuel et developpement futurs,” in Vol. 3éme conférence internationale DERBI, Perpignan juin, 2008.
[6] O. Ammar, “«Smart Grid» Réseau Electrique Intelligent,” 2017.
[7] M. Abarkan, N. K. M’Sirdi, and F. Errahimi, “MODELISATION ET SIMULATION D’UN SYSTEME DE PRODUCTION D’ENERGIE RENOUVELABLE MULTI-SOURCES ET MULTI-UTILISATEURS,” Rev. Méditerranéenne Télécommunications, Vol. 4, No. 2, 2014.
[8] Y. Sun, G. Sz\Hucs, and A. R. Brandt, “Solar PV output prediction from video streams using convolutional neural networks,” Energy Environ. Sci., Vol. 11, No. 7, pp. 1811–1818, 2018.
[9] C.-J. Huang and P.-H. Kuo, “Multiple-Input Deep Convolutional Neural Network Model for Short-Term Photovoltaic Power Forecasting,” IEEE Access, Vol. 7, pp. 74822–74834, 2019, doi: 10.1109/ACCESS.2019.2921238.
[10] H. Zhou, Y. Zhang, L. Yang, Q. Liu, K. Yan, and Y. Du, “Short-Term Photovoltaic Power Forecasting Based on Long Short Term Memory Neural Network and Attention Mechanism,” IEEE Access, Vol. 7, pp. 78063–78074, 2019, doi: 10.1109/ACCESS.2019.2923006.
[11] L. Wen, K. Zhou, S. Yang, and X. Lu, “Optimal load dispatch of community microgrid with deep learning based solar power and load forecasting,” Energy, vol. 171, pp. 1053–1065, Mar. 2019, doi: 10.1016/j.energy.2019.01.075.
[12] M. Abdel-Nasser and K. Mahmoud, “Accurate photovoltaic power forecasting models using deep LSTM-RNN,” Neural Comput. Appl., Vol. 31, No. 7, pp. 2727–2740, Jul. 2019, doi: 10.1007/s00521-017-3225-z.
[13] H. Sharadga, S. Hajimirza, and R. S. Balog, “Time series forecasting of solar power generation for large-scale photovoltaic plants,” Renew. Energy, Vol. 150, pp. 797–807, May 2020, doi: 10.1016/j.renene.2019.12.131.
[14] J. Zhang, Z. Tan, and Y. Wei, “An adaptive hybrid model for day-ahead photovoltaic output power prediction,” J. Clean. Prod., Vol. 244, p. 118858, 2020.
[15] M. Gao, J. Li, F. Hong, and D. Long, “Day-ahead power forecasting in a large-scale photovoltaic plant based on weather classification using LSTM,” Energy, Vol. 187, p. 115838, Nov. 2019, doi: 10.1016/j.energy.2019.07.168.
[16] G. W. Chang and H.-J. Lu, “Integrating Gray Data Preprocessor and Deep Belief Network for Day-Ahead PV Power Output Forecast,” IEEE Trans. Sustain. Energy, Vol. 11, No. 1, pp. 185–194, Jan. 2020, doi: 10.1109/TSTE.2018.2888548.
[17] F. Wang, Z. Xuan, Z. Zhen, K. Li, T. Wang, and M. Shi, “A day-ahead PV power forecasting method based on LSTM-RNN model and time correlation modification under partial daily pattern prediction framework,” Energy Convers. Manag., Vol. 212, p. 112766, 2020.
[18] B. Ray, R. Shah, Md. R. Islam, and S. Islam, “A New Data Driven Long-Term Solar Yield Analysis Model of Photovoltaic Power Plants,” IEEE Access, Vol. 8, pp. 136223–136233, 2020, doi: 10.1109/ACCESS.2020.3011982.
[19] G. Li, S. Xie, B. Wang, J. Xin, Y. Li, and S. Du, “Photovoltaic Power Forecasting With a Hybrid Deep Learning Approach,” IEEE Access, Vol. 8, pp. 175871–175880, 2020, doi: 10.1109/ACCESS.2020.3025860.
[20] P. Li, K. Zhou, X. Lu, and S. Yang, “A hybrid deep learning model for short-term PV power forecasting,” Appl. Energy, vol. 259, p. 114216, 2020.
[21] J. Ospina, A. Newaz, and M. O. Faruque, “Forecasting of PV plant output using hybrid wavelet-based LSTM-DNN structure model,” IET Renew. Power Gener., Vol. 13, No. 7, pp. 1087–1095, 2019, doi: 10.1049/iet-rpg.2018.5779.
[22] A. Alzahrani, P. Shamsi, C. Dagli, and M. Ferdowsi, “Solar Irradiance Forecasting Using Deep Neural Networks,” Procedia Comput. Sci., Vol. 114, pp. 304–313, Jan. 2017, doi: 10.1016/j.procs.2017.09.045.
[23] Z. Pang, F. Niu, and Z. O’Neill, “Solar radiation prediction using recurrent neural network and artificial neural network: A case study with comparisons,” Renew. Energy, Vol. 156, pp. 279–289, Aug. 2020, doi: 10.1016/j.renene.2020.04.042.
[24] M. C. Sorkun, C. Paoli, and Ö. D. Incel, “Time series forecasting on solar irradiation using deep learning,” in 2017 10th International Conference on Electrical and Electronics Engineering (ELECO), Nov. 2017, pp. 151–155.
[25] 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.
[26] M. A. F. B. Lima, P. C. M. Carvalho, L. M. Fernández-Ramírez, and A. P. S. Braga, “Improving solar forecasting using Deep Learning and Portfolio Theory integration,” Energy, Vol. 195, p. 117016, Mar. 2020, doi: 10.1016/j.energy.2020.117016.
[27] V. Suresh, P. Janik, J. M. Guerrero, Z. Leonowicz, and T. Sikorski, “Microgrid Energy Management System With Embedded Deep Learning Forecaster and Combined Optimizer,” IEEE Access, Vol. 8, pp. 202225–202239, 2020, doi: 10.1109/ACCESS.2020.3036131.
[28] Y. Q. Neo, T. T. Teo, W. L. Woo, T. Logenthiran, and A. Sharma, “Forecasting of photovoltaic power using deep belief network,” in TENCON 2017 - 2017 IEEE Region 10 Conference, Nov. 2017, pp. 1189–1194. doi: 10.1109/TENCON.2017.8228038.
[29] M. Mishra, P. Byomakesha Dash, J. Nayak, B. Naik, and S. Kumar Swain, “Deep learning and wavelet transform integrated approach for short-term solar PV power prediction,” Measurement, Vol. 166, p. 108250, Dec. 2020, doi: 10.1016/j.measurement.2020.108250.
[30] B. Gao, X. Huang, J. Shi, Y. Tai, and J. Zhang, “Hourly forecasting of solar irradiance based on CEEMDAN and multi-strategy CNN-LSTM neural networks,” Renew. Energy, Vol. 162, pp. 1665–1683, Dec. 2020, doi: 10.1016/j.renene.2020.09.141.
[31] P. Kumari and D. Toshniwal, “Extreme gradient boosting and deep neural network based ensemble learning approach to forecast hourly solar irradiance,” J. Clean. Prod., Vol. 279, p. 123285, Jan. 2021, doi: 10.1016/j.jclepro.2020.123285.
[32] Z. Zhen et al., “Deep learning based surface irradiance mapping model for solar PV power forecasting using sky image,” IEEE Trans. Ind. Appl., Vol. 56, No. 4, pp. 3385–3396, 2020.
[33] K. Wang, X. Qi, and H. Liu, “A comparison of day-ahead photovoltaic power forecasting models based on deep learning neural network,” Appl. Energy, Vol. 251, p. 113315, Oct. 2019, doi: 10.1016/j.apenergy.2019.113315.
[34] M. S. Hossain and H. Mahmood, “Short-Term Photovoltaic Power Forecasting using an LSTM Neural Network and Synthetic Weather Forecast,” IEEE Access, Vol. 8, pp. 172524–172533, 2020, doi: 10.1109/ACCESS.2020.3024901.
[35] K. Wang, X. Qi, and H. Liu, “Photovoltaic power forecasting based LSTM-Convolutional Network,” Energy, Vol. 189, p. 116225, Dec. 2019, doi: 10.1016/j.energy.2019.116225.
[36] R. Ahmed, V. Sreeram, Y. Mishra, and M. D. Arif, “A review and evaluation of the state-of-the-art in PV solar power forecasting: Techniques and optimization,” Renew. Sustain. Energy Rev., Vol. 124, p. 109792, 2020.
[37] Z. Niu, Z. Yu, W. Tang, Q. Wu, and M. Reformat, “Wind power forecasting using attention-based gated recurrent unit network,” Energy, Vol. 196, p. 117081, 2020.
[38] M. Massaoudi, I. Chihi, L. Sidhom, M. Trabelsi, S. S. Refaat, and F. S. Oueslati, “Enhanced Random Forest Model for Robust Short-Term Photovoltaic Power Forecasting Using Weather Measurements,” Energies, Vol. 14, No. 13, Art. No. 13, Jan. 2021, doi: 10.3390/en14133992.
[39] D. Liu and K. Sun, “Random forest solar power forecast based on classification optimization,” Energy, Vol. 187, p. 115940, Nov. 2019, doi: 10.1016/j.energy.2019.115940.
[40] A. B. K. Didavi, R. G. Agbokpanzo, and M. Agbomahena, “Comparative study of Decision Tree, Random Forest and XGBoost performance in forecasting the power output of a photovoltaic system,” in 2021 IEEE 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART), Dec. 2021, pp. 1–5. doi: 10.1109/BioSMART54244.2021.9677566.
[41] Rahul, A. Gupta, A. Bansal, and K. Roy, “Solar Energy Prediction using Decision Tree Regressor,” in 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS), May 2021, pp. 489–495. doi: 10.1109/ICICCS51141.2021.9432322.
[42] N. Singh, S. Jena, and C. K. Panigrahi, “A novel application of Decision Tree classifier in solar irradiance prediction,” Mater. Today Proc., Vol. 58, pp. 316–323, Jan. 2022, doi: 10.1016/j.matpr.2022.02.198.
[43] C. N. Obiora, A. Ali, and A. N. Hasan, “Implementing Extreme Gradient Boosting (XGBoost) Algorithm in Predicting Solar Irradiance,” in 2021 IEEE PES/IAS PowerAfrica, Aug. 2021, pp. 1–5. doi: 10.1109/PowerAfrica52236.2021.9543159.
[44] D.-J. Bae, B.-S. Kwon, and K.-B. Song, “XGBoost-Based Day-Ahead Load Forecasting Algorithm Considering Behind-the-Meter Solar PV Generation,” Energies, Vol. 15, No. 1, Art. No. 1, Jan. 2022, doi: 10.3390/en15010128.
[45] Q.-T. Phan, Y.-K. Wu, and Q.-D. Phan, “Short-term Solar Power Forecasting Using XGBoost with Numerical Weather Prediction,” in 2021 IEEE International Future Energy Electronics Conference (IFEEC), Nov. 2021, pp. 1–6. doi: 10.1109/IFEEC53238.2021.9661874.
[46] R. Gupta, A. K. Yadav, S. Jha, and P. K. Pathak, “Time Series Forecasting of Solar Power Generation using Facebook Prophet and XG Boost,” in 2022 IEEE Delhi Section Conference (DELCON), Feb. 2022, pp. 1–5. doi: 10.1109/DELCON54057.2022.9752916.
[47] X. Li et al., “Probabilistic solar irradiance forecasting based on XGBoost,” Energy Rep., Vol. 8, pp. 1087–1095, Aug. 2022, doi: 10.1016/j.egyr.2022.02.251.
[48] M. Massaoudi et al., “An Effective Hybrid NARX-LSTM Model for Point and Interval PV Power Forecasting,” IEEE Access, Vol. 9, pp. 36571–36588, 2021, doi: 10.1109/ACCESS.2021.3062776.
[49] A. R. Gilles, D. Audace, H. Aristide, O. Arouna, and E. Christophe, “Evaluation of the photovoltaic power prediction performance of a neural network based on input data,” in 2020 IEEE 2nd International Conference on Smart Cities and Communities (SCCIC), Dec. 2020, pp. 1–6. doi: 10.1109/SCCIC51516.2020.9377334.
[50] H. Nazaripouya, B. Wang, Y. Wang, P. Chu, H. R. Pota, and R. Gadh, “Univariate time series prediction of solar power using a hybrid wavelet-ARMA-NARX prediction method,” in 2016 IEEE/PES Transmission and Distribution Conference and Exposition (T&D), May 2016, pp. 1–5. doi: 10.1109/TDC.2016.7519959.
[51] M. Massaoudi, I. Chihi, L. Sidhom, M. Trabelsi, S. S. Refaat, and F. S. Oueslati, “A Novel Approach Based Deep RNN Using Hybrid NARX-LSTM Model for Solar Power Forecasting.” arXiv, Oct. 21, 2019. doi: 10.48550/arXiv.1910.10064.
[52] Z. Boussaada, O. Curea, A. Remaci, H. Camblong, and N. Mrabet Bellaaj, “A Nonlinear Autoregressive Exogenous (NARX) Neural Network Model for the Prediction of the Daily Direct Solar Radiation,” Energies, Vol. 11, No. 3, Art. No. 3, Mar. 2018, doi: 10.3390/en11030620.
[53] “JRC Photovoltaic Geographical Information System (PVGIS) - European Commission.” https://re.jrc.ec.europa.eu/pvg_tools/en/ (accessed Jul. 08, 2022).
[54] A. Abu-Rmileh, “Be careful when interpreting your features importance in XGBoost!,” Medium, Sep. 02, 2021. https://towardsdatascience.com/be-careful-when-interpreting-your-features-importance-in-xgboost-6e16132588e7 (accessed May 16, 2022).
[55] “Rk200-04 Solar Radiation Sensor Solar Irradiance Sensor | Rika Sensors.” https://www.rikasensor.com/rk200-04-solar-radiation-sensor-solar-irradiance-sensor.html (accessed Jul. 23, 2022).
[56] “Rk330-01b Atmospheric Temperature, Humidity & Pressure Sensor | Rika Sensors.” https://www.rikasensor.com/rk330-01b-atmospheric-temperature-humidity-pressure-sensor.html (accessed Jul. 23, 2022).
[57] “Rk100-02 Cheap Plastic Wind Speed Sensor / Detector, 3 Cup Wind Anemometer | Rika.” https://www.rikasensor.com/rk100-02-wind-speed-sensor-wind-speed-detector.html (accessed Jul. 23, 2022).
)