Integrating Temporal and Feedforward Models for Solar Energy Prediction: LSTM and ANN Hybrid Approaches
DOI:
https://doi.org/10.53893/ijrvocas.v4i2.317Keywords:
Agrivoltaic, Deep learning, Hybrid LSTM-ANN, LSTM, Solar EnergyAbstract
The increasing reliance on renewable energy, particularly solar power, necessitates accurate models for predicting energy output to optimize storage and distribution systems. Traditional methods such as Long Short-Term Memory (LSTM) networks and Artificial Neural Networks (ANNs) offer unique strengths in forecasting photovoltaic (PV) system outputs. LSTM excels in capturing temporal dependencies in time-series data, while ANNs effectively model nonlinear relationships between variables. This study aims to develop and evaluate a hybrid LSTM-ANN model for improving the accuracy of PV energy output predictions, focusing on voltage, power, and irradiance. Using data collected from a solar-powered greenhouse in Talang Kemang, Indonesia, the model was trained and validated. The hybrid model demonstrated significant improvements in prediction accuracy. For voltage, the model achieved a Mean Absolute Error (MAE) of 0.1016 and a Root Mean Squared Error (RMSE) of 0.1417, while irradiance predictions resulted in an MAE of 0.0895 and RMSE of 0.1149. Power predictions also yielded strong results, with an MAE of 0.1506 and RMSE of 0.1954. These results highlight the hybrid LSTM-ANN model's effectiveness in combining temporal and nonlinear data processing capabilities, leading to superior accuracy in predicting PV system outputs. This approach can enhance the reliability of energy forecasting models, enabling better integration of solar power into electrical grids. The model holds promise for broader applications in renewable energy systems, improving their efficiency and sustainability
References
Agga, A., Abbou, A., Labbadi, M., El Houm, Y., & Hammou Ou Ali, I. (2022). CNN-LSTM: An efficient hybrid deep learning architecture for predicting short-term photovoltaic power production. Electric Power Systems Research, 208, 107908. https://doi.org/10.1016/j.epsr.2022.107908
Al-Hajj, R., Assi, A., Fouad, M. M., & Hossam, E. (2021). A hybrid LSTM-based genetic programming approach for short-term prediction of global solar radiation using weather data. Processes, 9(7), 1187. https://doi.org/10.3390/pr9071187
Asrari, A., Wu, T., & Ramos, B. (2017). A hybrid algorithm for short-term solar power prediction—Sunshine state case study. IEEE Transactions on Sustainable Energy, 8(2), 582-591. https://doi.org/10.1109/TSTE.2016.2613962
Battisti, F., Silva, A., Pereira, L. F., & Dias, T. (2022). hLSTM-Aging: A hybrid LSTM model for software aging forecast. Applied Sciences, 12(13), 6412. https://doi.org/10.3390/app12136412
Castillo-Rojas, W., Bekios-Calfa, J., & Zamora, C. (2023). Daily prediction model of photovoltaic power generation using a hybrid architecture of recurrent neural networks and shallow neural networks. International Journal of Photoenergy, 2023(8), 19. https://doi.org/10.1155/2023/2592405
Chen, S., Li, C., Stull, R., & Li, M. (2024). Improved satellite-based intra-day solar forecasting with a chain of deep learning models. Energy Conversion and Management, 313, 118598. https://doi.org/10.1016/j.enconman.2024.118598
Díaz-Bedoya, D., González-Rodríguez, M., Clairand, J.-M., Serrano-Guerrero, X., & Escrivá-Escrivá, G. (2023). Forecasting univariate solar irradiance using machine learning models: A case study of two Andean cities. Energy Conversion and Management, 296, 117618. https://doi.org/10.1016/j.enconman.2023.117618
Garud, K., Jayaraj, S., & Lee, M.-Y. (2020). A review on modeling of solar photovoltaic systems using artificial neural networks, fuzzy logic, genetic algorithm, and hybrid models. International Journal of Energy Research, 45(7). https://doi.org/10.1002/er.5608
Ibrahim, M. S., & Morkos, S. (2024). A hybrid model of CNN and LSTM autoencoder-based short-term PV power generation forecasting. Electrical Engineering, 106(4), 1-17. https://doi.org/10.1007/s00202-023-02220-8
Javaid, A., Sajid, M., Uddin, E., Waqas, A., & Ayaz, Y. (2024). Sustainable urban energy solutions: Forecasting energy production for hybrid solar-wind systems. Energy Conversion and Management, 302, 118120. https://doi.org/10.1016/j.enconman.2024.118120
Jouane, Y., Sow, M. C., & Belkhouche, O. (2023). Forecasting photovoltaic energy for a winter house using a hybrid deep learning model. In 2023 12th International Conference on Renewable Energy Research and Applications (ICRERA), Oshawa, ON, Canada. https://doi.org/10.1109/ICRERA59003.2023.10269444
Kim, B., Suh, D.-H., Otto, M., & Huh, J. (2021). A novel hybrid spatio-temporal forecasting of multisite solar photovoltaic generation. Remote Sensing, 13(13), 2605. https://doi.org/10.3390/rs13132605
Krishnan, M., Jung, Y., & Yun, S. (2020). Prediction of energy demand in smart grid using hybrid approach. In 2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC), Erode, India. https://doi.org/10.1109/ICCMC48092.2020.ICCMC-00055
Maham, F. H., & Akarslan, E. (2022). Design of a hybrid method exploiting different insolation states for solar radiation forecasting. Afyon Kocatepe University Journal of Electrical Engineering, 22(3), 588-596. https://doi.org/10.35414/akufemubid.1074290
Madondo, M. & Gibbons, T. (2018). Learning and Modeling Chaos Using LSTM Recurrent Neural Networks. In Proceedings of the Midwest Instruction and Computing Symposium, Duluth, Minnesota, 6–7 April 2018.
Mukhtar, M., Oluwasanmi, A., Yimen, N., et al. (2022). Development and comparison of two novel hybrid neural network models for hourly solar radiation prediction. Applied Sciences, 12(3), 1435. https://doi.org/10.3390/app12031435
Mukhtar, M., Oluwasanmi, A., Yimen, N., Qinxi, Z., Ukwuoma, C. C., Ezurike, B., & Bamisile, O. (2020). Development and comparison of two novel hybrid neural network models for hourly solar radiation prediction. Applied Sciences, 12(3), 1435. https://doi.org/10.3390/app12031435
Oktarina, Y., Nawawi, Z., Suprapto, B. Y., & Dewi, T. (2023). Digitized smart solar powered agriculture implementation in Palembang, South Sumatra. In 2023 10th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), 60-65. https://doi.org/10.1109/EECSI59885.2023.10295805
Oktarina, Y., Nawawi, Z., Suprapto, B. Y., & Dewi, T. (2023). Solar powered greenhouse for smart agriculture. In 2023 International Conference on Electrical and Information Technology (IEIT), 36-42. https://doi.org/10.1109/IEIT59852.2023.10335599
Phan, Q.-T., Wu, Y.-K., & Phan, Q. (2022). An approach using transformer-based model for short-term PV generation forecasting. In 2022 8th International Conference on Applied System Innovation (ICASI), Nantou, Taiwan. https://doi.org/10.1109/ICASI55125.2022.9774491
Rahman, M., Shakeri, M., Tiong, S., & Wong, K. P. (2021). Prospective methodologies in hybrid renewable energy systems for energy prediction using artificial neural networks. Sustainability, 13(4), 2393. https://doi.org/10.3390/su13042393
Sahu, S., Srivastava, N., Arora, P., Natu, I., Bhosale, A. C., Singh, R., Tiwari, D., & Saini, V. (2024). Techno-enviro-economic evaluation of decentralized solar ammonia production plant in India under various energy supply scenarios. Energy Conversion and Management, 318, 118908. https://doi.org/10.1016/j.enconman.2024.118908
Sansine, V., Ortega, P., Hissel, D., & Santin, M. (2022). Solar irradiance probabilistic forecasting using machine learning, metaheuristic models, and numerical weather predictions. Sustainability, 14(22), 15260. https://doi.org/10.3390/su142215260
Sun, M., Zhang, Z., Zhou, Y., Xu, Z., & Chen, L. (2021). Convolution and long short-term memory neural network for PECVD process quality prediction. In 2021 IEEE Reliability and Prognostics and Health Management (PHM-Nanjing), China. https://doi.org/10.1109/PHMNanjing52125.2021.9612756
Sushmit, M. M., & Mahbubul, I. M. (2023). Forecasting solar irradiance with hybrid classical–quantum models: A comprehensive evaluation of deep learning and quantum-enhanced techniques. Energy Conversion and Management, 294, 117555. https://doi.org/10.1016/j.enconman.2023.117555
Tahir, M. F., Tzes, A., & Yousaf, M. Z. (2024). Enhancing PV power forecasting with deep learning and optimizing solar PV project performance with economic viability: A multi-case analysis of 10MW Masdar project in UAE. Energy Conversion and Management, 311, 118549. https://doi.org/10.1016/j.enconman.2024.118549
Tovar, M., Robles, M., & Rashid, F. (2020). PV power prediction using CNN-LSTM hybrid neural network model: Case study: Temixco-Morelos, México. Energies, 13(24), 6512. https://doi.org/10.3390/en13246512
Tufail, S., Tariq, M., Batool, S., & Iqbal, A. (2023). Comparative analysis between feedforward neural network and CNN-LSTM neural network to predict household electrical energy consumption. In 2023 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), Tenerife, Canary Islands, Spain. https://doi.org/10.1109/ICECCME57830.2023.10253452
Wentz, V. H., Maciel, J. N., Pereira, J. W., & Souza, S. C. (2022). Solar irradiance forecasting to short-term PV power: Accuracy comparison of ANN and LSTM models. Energies, 15(7), 2457. https://doi.org/10.3390/en15072457
Zafar, A., Che, Y., Ahmed, M., & Khan, M. Y. (2023). Enhancing power generation forecasting in smart grids using hybrid autoencoder long short-term memory machine learning model. IEEE Access, 11, 118521-118537. https://doi.org/10.1109/ACCESS.2023.3326415
Zafar, A., Che, Y., Sehnan, M., & Habib, U. (2024). Optimizing solar power generation forecasting in smart grids: A hybrid convolutional neural network-autoencoder long short-term memory approach. Physica Scripta, Environmental Science, Engineering, Computer Science. https://doi.org/10.1088/1402-4896/acb117
Zaman, M., Saha, S., Eini, R., & Abdelwahed, S. (2021). A deep learning model for forecasting photovoltaic energy with uncertainties. In 2021 IEEE Green Energy and Smart Systems Conference (IGESSC), Long Beach, CA, USA. https://doi.org/10.1109/IGESSC53124.2021.96186881
Zhou, F., Chen, Y., & Liu, J. (2023). Application of a new hybrid deep learning model that considers temporal and feature dependencies in rainfall-runoff simulation. Remote Sensing, 15(5), 1-1395. https://doi.org/10.3390/rs15051395
Zhu, Y., Li, M., Ma, X., Wang, Y., Li, G., Zhang, Y., Liu, Y., & Hassanien, R. H. E. (2024). Solar irradiance prediction with variable time lengths and multi-parameters in full climate conditions based on photovoltaic greenhouse. Energy Conversion and Management, 315, 118758. https://doi.org/10.1016/j.enconman.2024.118758
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Yurni Oktarina, Zainuddin Nawawi, Bhakti Yudho Suprapto, Tresna Dewi
This work is licensed under a Creative Commons Attribution 4.0 International License.
