Short Term Forecasting of Solar Irradiance Using Ensemble CNN-BiLSTM-MLP Model Combined with Error Minimization and CEEMDAN Pre-Processing Technique

Document Type : Original Article


1 Department of Mechatronics Engineering, Chandigarh University, Mohali, India

2 Department of Electronics and Communication Engineering, Chandigarh University, Mohali, India



Solar energy forecasting is necessary due to its variable and fluctuating nature, but it is also a challenge to predict accurately behaviour of solar irradiation. To capture this, the proposed methodology uses an ensemble model combined with error minimization and CEEMDAN Pre-processing technique. In this paper, data of two locations are used to predict short term forecasting of solar irradiation using seven developed models based on the proposed procedure. The use of hourly forecasting, CEEMDAN method, error minimization and ensemble hybrid model enhance the anti-interference capability of all developed model. Four-year data of New Delhi and Ahmedabad is used and sourced from NSRDB website. Out of all the proposed models CEEMDAN-CNN-BiLSTM-MLP with CEEMDAN_IMF_18 configured signal processing approach achieved least average RMSE, n-RMSE and MAE of both locations with values 13.215 W/m2, 7.13% and 8.605 W/m2 respectively and have maximum average R2 (99.205%). When compared to persistence model, proposed model with this configuration was able to outperform with average percentage improvement 87.63%, 86.78%, 87.17% and 17.875% in terms of  , ,  and   respectively. The proposed model outperforms existing techniques for solar irradiation forecasting, demonstrating greater efficiency and reliability, making it a valuable reference for future performance optimization.


[1] R. A. A. Ramadhan, Y. R. J. Heatubun, S. F. Tan, and H.-J. Lee, “Comparison of physical and machine learning models for estimating solar irradiance and photovoltaic power,” Renew Energy, vol. 178, pp. 1006–1019, Nov. 2021, doi: 10.1016/j.renene.2021.06.079.
[2] P. Kumari and D. Toshniwal, “Long short term memory–convolutional neural network based deep hybrid approach for solar irradiance forecasting,” Appl Energy, vol. 295, p. 117061, Aug. 2021, doi: 10.1016/j.apenergy.2021.117061.
[3] Z. Ma et al., “Application of hybrid model based on double decomposition, error correction and deep learning in short-term wind speed prediction,” Energy Convers Manag, vol. 205, p. 112345, Feb. 2020, doi: 10.1016/j.enconman.2019.112345.
[4] W. Wang, K. Chau, L. Qiu, and Y. Chen, “Improving forecasting accuracy of medium and long-term runoff using artificial neural network based on EEMD decomposition,” Environ Res, vol. 139, pp. 46–54, May 2015, doi: 10.1016/j.envres.2015.02.002.
[5] K. Yan, J. Huang, W. Shen, and Z. Ji, “Unsupervised learning for fault detection and diagnosis of air handling units,” Energy Build, vol. 210, p. 109689, Mar. 2020, doi: 10.1016/j.enbuild.2019.109689.
[6] H. Zhou, Q. Liu, K. Yan, and Y. Du, “Deep Learning Enhanced Solar Energy Forecasting with AI-Driven IoT,” Wirel Commun Mob Comput, vol. 2021, pp. 1–11, Jun. 2021, doi: 10.1155/2021/9249387.
[7] Z. Feng, W. Niu, X. Wan, B. Xu, F. Zhu, and J. Chen, “Hydrological time series forecasting via signal decomposition and twin support vector machine using cooperation search algorithm for parameter identification,” J Hydrol (Amst), vol. 612, p. 128213, Sep. 2022, doi: 10.1016/j.jhydrol.2022.128213.
[8] S. Iqbal, S. N. Khan, M. Sajid, J. Khan, Y. Ayaz, and A. Waqas, “Impact and performance efficiency analysis of grid-tied solar photovoltaic system based on installation site environmental factors,” Energy & Environment, vol. 34, no. 7, pp. 2343–2363, Nov. 2023, doi: 10.1177/0958305X221106618.
[9] R. J. Mustafa, M. R. Gomaa, M. Al-Dhaifallah, and H. Rezk, “Environmental Impacts on the Performance of Solar Photovoltaic Systems,” Sustainability, vol. 12, no. 2, p. 608, Jan. 2020, doi: 10.3390/su12020608.
[10] P. Gupta and R. Singh, “PV power forecasting based on data-driven models: a review,” International Journal of Sustainable Engineering, vol. 14, no. 6, pp. 1733–1755, Nov. 2021, doi: 10.1080/19397038.2021.1986590.
[11] S. Salcedo-Sanz, R. C. Deo, L. Cornejo-Bueno, C. Camacho-Gómez, and S. Ghimire, “An efficient neuro-evolutionary hybrid modelling mechanism for the estimation of daily global solar radiation in the Sunshine State of Australia,” Appl Energy, vol. 209, pp. 79–94, Jan. 2018, doi: 10.1016/j.apenergy.2017.10.076.
[12] W. VanDeventer et al., “Short-term PV power forecasting using hybrid GASVM technique,” Renew Energy, vol. 140, pp. 367–379, Sep. 2019, doi: 10.1016/j.renene.2019.02.087.
[13] A. Shadab, S. Ahmad, and S. Said, “Spatial forecasting of solar radiation using ARIMA model,” Remote Sens Appl, vol. 20, p. 100427, Nov. 2020, doi: 10.1016/j.rsase.2020.100427.
[14] “Predictive Modelling of Global Solar Radiation with Artificial Intelligence Approaches using MODIS Satellites and Atmospheric Reanalysis Data for Australia.”
[15] H. Zang et al., “Estimation and validation of daily global solar radiation by day of the year-based models for different climates in China,” Renew Energy, vol. 135, pp. 984–1003, May 2019, doi: 10.1016/j.renene.2018.12.065.
[16] J. Dong, T. Kuruganti, and S. M. Djouadi, “Very short-term photovoltaic power forecasting using uncertain basis function,” in 2017 51st Annual Conference on Information Sciences and Systems (CISS), IEEE, Mar. 2017, pp. 1–6. doi: 10.1109/CISS.2017.7926158.
[17] Y. Deng, B. Wang, and Z. Lu, “A hybrid model based on data preprocessing strategy and error correction system for wind speed forecasting,” Energy Convers Manag, vol. 212, p. 112779, May 2020, doi: 10.1016/J.ENCONMAN.2020.112779.
[18] R. K. Sahu, B. Shaw, J. R. Nayak, and Shashikant, “Short/medium term solar power forecasting of Chhattisgarh state of India using modified TLBO optimized ELM,” Engineering Science and Technology, an International Journal, vol. 24, no. 5, pp. 1180–1200, Oct. 2021, doi: 10.1016/J.JESTCH.2021.02.016.
[19] C. Li, Y. Zhang, G. Zhao, and Y. Ren, “Hourly solar irradiance prediction using deep BiLSTM network,” Earth Sci Inform, vol. 14, no. 1, pp. 299–309, Mar. 2021, doi: 10.1007/s12145-020-00511-3.
[20] P. Singla, M. Duhan, and S. Saroha, “An integrated framework of robust local mean decomposition and bidirectional long short-term memory to forecast solar irradiance,” Int J Green Energy, vol. 20, no. 10, pp. 1073–1085, Aug. 2023, doi: 10.1080/15435075.2022.2143272.
[21] C. Feng, J. Zhang, W. Zhang, and B.-M. Hodge, “Convolutional neural networks for intra-hour solar forecasting based on sky image sequences,” Appl Energy, vol. 310, p. 118438, Mar. 2022, doi: 10.1016/j.apenergy.2021.118438.
[22] S. Fatima, V. Püvi, M. Pourakbari‐Kasmaei, and M. Lehtonen, “Photovoltaic hosting capacity improvement based on the economic comparison between curtailment and network upgrade,” IET Generation, Transmission & Distribution, vol. 17, no. 17, pp. 3848–3860, Sep. 2023, doi: 10.1049/gtd2.12936.
[23] Z. WU and N. E. HUANG, “ENSEMBLE EMPIRICAL MODE DECOMPOSITION: A NOISE-ASSISTED DATA ANALYSIS METHOD,” Adv Adapt Data Anal, vol. 01, no. 01, pp. 1–41, Jan. 2009, doi: 10.1142/S1793536909000047.
[24] R. Kumar Srivastava and A. Gupta, “Short term solar irradiation forecasting using Deep neural network with decomposition methods and optimized by grid search algorithm,” E3S Web of Conferences, vol. 405, p. 02011, Jul. 2023, doi: 10.1051/e3sconf/202340502011.
[25] R. Prasad, M. Ali, Y. Xiang, and H. Khan, “A double decomposition-based modelling approach to forecast weekly solar radiation,” Renew Energy, vol. 152, pp. 9–22, Jun. 2020, doi: 10.1016/j.renene.2020.01.005.
[26] X. Huang et al., “Hybrid deep neural model for hourly solar irradiance forecasting,” Renew Energy, vol. 171, pp. 1041–1060, Jun. 2021, doi: 10.1016/j.renene.2021.02.161.
[27] J. Tong, L. Xie, S. Fang, W. Yang, and K. Zhang, “Hourly solar irradiance forecasting based on encoder–decoder model using series decomposition and dynamic error compensation,” Energy Convers Manag, vol. 270, p. 116049, Oct. 2022, doi: 10.1016/j.enconman.2022.116049.
[28] P. Singla, M. Duhan, and S. Saroha, “An ensemble method to forecast 24-h ahead solar irradiance using wavelet decomposition and BiLSTM deep learning network,” Earth Sci Inform, vol. 15, no. 1, pp. 291–306, Mar. 2022, doi: 10.1007/s12145-021-00723-1.
[29] A. Zarei and N. Ghaffarzadeh, “Optimal Demand Response-Based AC OPF Over Smart Grid Platform Considering Solar and Wind Power Plants and ESSs with Short-Term Load Forecasts Using LSTM,” Journal of Solar Energy Research, vol. 8, no. 2, pp. 1367–1379, Apr. 2023, doi: 10.22059/JSER.2023.352567.1271.
[30] M. Bhargva, M. Sharma, A. Yadav, N. K. Batra, and R. K. Behl, “Productivity Augmentation of a Solar Still with Rectangular Fins and Bamboo Cotton Wick,” Journal of Solar Energy Research, vol. 8, no. 2, pp. 1410–1416, Apr. 2023, doi: 10.22059/jser.2023.356414.1279.
[31] S. Dorel, M. Gmal Osman, C.-V. Strejoiu, and G. Lazaroiu, “Exploring Optimal Charging Strategies for Off-Grid Solar Photovoltaic Systems: A Comparative Study on Battery Storage Techniques,” Batteries, vol. 9, no. 9, p. 470, Sep. 2023, doi: 10.3390/batteries9090470.
[32] E. Akpinar, A. Balikci, E. Durbaba, and B. T. Azizoglu, “Single-Phase Transformerless Photovoltaic Inverter With Suppressing Resonance in Improved H6,” IEEE Trans Power Electron, vol. 34, no. 9, pp. 8304–8316, Sep. 2019, doi: 10.1109/TPEL.2018.2886054.
[33] L. Pan, X. Xu, J. Liu, and W. Hu, “Adaptive robust scheduling of a hydro/photovoltaic/pumped-storage hybrid system in day-ahead electricity and hydrogen markets,” Sustain Cities Soc, vol. 95, p. 104571, Aug. 2023, doi: 10.1016/j.scs.2023.104571.
[34] A. Gupta and K. Gupta, “Short Term Solar Irradiation Prediction Framework Based on EEMD-GA-LSTM Method,” Strategic Planning for Energy and the Environment, pp. 255–280, Feb. 2023, doi: 10.13052/spee1048-5236.4132.
[35] A. Gupta, K. Gupta, and sumit Saroha, “Short Term Solar Irradiation Forecasting using CEEMDAN Decomposition Based BiLSTM Model Optimized by Genetic Algorithm Approach.,” International Journal of Renewable Energy Development , vol. 11, no. 3, 2022.