LOAD POWER PREDICTION IN SMART SOLAR MICROGRID BASED GATED RECURRENT UNIT
DOI:
https://doi.org/10.62985/j.huit_ojs.vol26.no2E.414Keywords:
Load power prediction, gated recurrent unit, smart solar microgrid, recurrent neural networkAbstract
Accurate load power prediction plays a critical role in smart solar microgrids by enabling efficient energy management and optimal power flow control. This paper proposes a load power forecasting approach based on the Gated Recurrent Unit (GRU) neural network to address the nonlinear and time-dependent characteristics of microgrid load profiles. The proposed GRU model is optimized using a grid search strategy to systematically determine key hyperparameters, thereby enhancing prediction accuracy and model stability. Historical load and operational data from a smart solar microgrid are utilized for model training and validation. To demonstrate the effectiveness of the proposed approach, the GRU model is compared with a traditional Recurrent Neural Network (RNN). Experimental results indicate that the GRU-based model consistently outperforms the RNN in terms of evaluation metrics, including loss, mean absolute error (MAE), and mean absolute percentage error (MAPE). The findings confirm that the optimized GRU model provides an effective and reliable tool for load power prediction, supporting intelligent control and energy management in smart solar microgrid systems.
References
[1] 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, 2019, doi: https://doi.org/10.1016/j.energy.2019.01.075.
[2] S. Aslam, H. Herodotou, S. M. Mohsin, N. Javaid, N. Ashraf, and S. Aslam, “A survey on deep learning methods for power load and renewable energy forecasting in smart microgrids,” Renew. Sustain. Energy Rev., vol. 144, Art. no. 110992, 2021, doi: https://doi.org/10.1016/j.rser.2021.110992.
[3] C. Singh and A. R. Garg, “Enhancing solar power output predictions: Analyzing ARIMA and S-ARIMA models for short-term forecasting,” in Proc. IEEE 11th Power India Int. Conf. (PIICON), 2024, pp. 1–5, doi: https://doi.org/10.1109/PIICON63519.2024.10995070.
[4] R. Huang, T. Huang, R. Gadh, and N. Li, “Solar generation prediction using the ARMA model in a laboratory-level micro-grid,” in Proc. IEEE 3rd Int. Conf. Smart Grid Commun. (SmartGridComm), 2012, pp. 528–533, doi: https://doi.org/10.1109/SmartGridComm.2012.6486039.
[5] M. H. Alsharif, M. K. Younes, and J. Kim, “Time series ARIMA model for prediction of daily and monthly average global solar radiation: The case study of Seoul, South Korea,” Symmetry, vol. 11, no. 2, Art. no. 240, 2019, doi: https://doi.org/10.3390/sym11020240.
[6] F. Rodríguez, A. Fleetwood, A. Galarza, and L. Fontán, “Predicting solar energy generation through artificial neural networks using weather forecasts for microgrid control,” Renew. energy, vol. 126, pp. 855–864, 2018, doi: https://doi.org/10.1016/j.renene.2018.03.070.
[7] M. G. M. Abdolrasol, R. Mohamed, M. A. Hannan, A. Q. Al-Shetwi, M. Mansor, and F. Blaabjerg, “Artificial neural network based particle swarm optimization for microgrid optimal energy scheduling,” IEEE Trans. Power Electron., vol. 36, no. 11, pp. 12151–12157, 2021, doi: https://doi.org/10.1109/TPEL.2021.3074964.
[8] V. Y. Kondaiah, B. Saravanan, P. Sanjeevikumar, and B. Khan, “A review on short‐term load forecasting models for micro‐grid application,” J. Eng., vol. 2022, no. 7, pp. 665-689, 2022, doi: https://doi.org/10.1049/tje2.12151.
[9] T. Nguyen Da, M.-Y. Cho, and P. Nguyen Thanh, “Optimizing K-means clustering center selection with density-based spatial cluster in radial basis function neural network for load forecasting of smart solar microgrid,” Electr. Eng., vol. 107, pp. 8963–8978, 2025, doi: https://doi.org/10.1007/s00202-024-02599-y.
[10] T. P. Nguyen, C.-T. Yeh, M. Cho, and Y. Huang, “Complementary grid power prediction using artificial neural network in the energy management system of a disaster prevention smart solar microgrid,” Int. J. Smart Grid Clean Energy, vol. 9, no. 5, pp. 879–889, 2020, doi: https://doi.org/10.12720/sgce.9.5.879-889.
[11] P. Malik, A. Gehlot, R. Singh, L. R. Gupta, and A. K. Thakur, “A review on ANN based model for solar radiation and wind speed prediction with real-time data,” Arch. Comput. Methods Eng., vol. 29, no. 5, pp. 3183–3201, 2022, doi: https://doi.org/10.1007/s11831-021-09687-3.
[12] H. Hasan, M. R. Munawar, and R. H. Siregar, “Neural network-based solar irradiance forecast for peak load management of grid-connected microgrid with photovoltaic distributed generation,” in Proc. 2017 Int. Conf. Electrical Engineering and Informatics (ICELTICs), 2017, pp. 87–90, doi: https://doi.org/10.1109/ICELTICS.2017.8253235.
[13] E. Akarslan and F. O. Hocaoglu, “Electricity demand forecasting of a microgrid using ANN,” in Proc. 2018 9th Int. Renewable Energy Congr. (IREC), 2018, pp. 1–5, doi: doi: https://doi.org/10.1109/IREC.2018.8362471.
[14] D. O’Leary and J. Kubby, “Feature selection and ANN solar power prediction,” J. Renew. Energy, vol. 2017, no. 1, Art. no. 2437387, 2017, doi: https://doi.org/10.1155/2017/2437387.
[15] H. A. Sayed, A. William, and A. M. Said, “Smart electricity meter load prediction in Dubai using MLR, ANN, RF, and ARIMA,” Electronics, vol. 12, no. 2, Art. no. 389, 2023, doi: https://doi.org/10.3390/electronics12020389.
[16] D. Kumar, H. D. Mathur, S. Bhanot, and R. C. Bansal, “Forecasting of solar and wind power using LSTM RNN for load frequency control in isolated microgrid,” Int. J. Model. Simul., vol. 41, no. 4, pp. 311–323, 2021, doi: https://doi.org/10.1080/02286203.2020.1767840.
[17] K. N. Le Kim, T. N. Quoc, and P. N. Thanh, “Deep learning method for load forecast in smart solar system based long short-term memory,” in Proc. 2024 8th Int. Artificial Intelligence and Data Processing Symp. (IDAP), 2024, pp. 1–5, doi: https://doi.org/10.1109/IDAP64064.2024.10710960.
[18] T. N. Da, M. Cho, and P. N. Thanh, “Hourly load prediction based feature selection scheme and hybrid CNN-LSTM method for building’s smart solar microgrid,” Expert Syst., vol. 41, no. 7, Art. no. e13539, 2024, doi: https://doi.org/10.1111/exsy.13539.
[19] C.-H. Lee, P. Nguyen Thanh, C.-T. Yeh, and M.-Y. Cho, “Three-phase load prediction-based hybrid convolution neural network combined bidirectional long short-term memory in solar power plant,” Int. Trans. Electr. Energy Syst., vol. 2022, no. 1, Art. no. 2870668, 2022, doi: https://doi.org/10.1155/2022/2870668.
[20] T. N. Da, L. Yimin, C. L. Peng, M.-Y. Cho, K. N. Le Kim, and P. N. Thanh, “Short-term solar power prediction using long short-term memory in solar plant with deep learning machine,” in Proc. 2022 6th Int. Conf. Green Technology and Sustainable Development (GTSD), 2022, pp. 651–656, doi: https://doi.org/10.1109/GTSD54989.2022.9989035.
[21] C.-T. Yeh, P. N. Thanh, M.-Y. Cho, and T. N. Quoc, “Short-term load power prediction based deep learning gated recurrent unit in solar power plant,” in Proc. 2022 5th Asia Conf. Energy and Electrical Engineering (ACEEE), 2022, pp. 36–40, doi: https://doi.org/10.1109/ACEEE56193.2022.9851878.
[22] P. N. Thanh, M.-Y. Cho, C.-L. Chang, and M.-J. Chen, “Short-term three-phase load prediction with advanced metering infrastructure data in smart solar microgrid based convolution neural network bidirectional gated recurrent unit,” IEEE Access, vol. 10, pp. 68686–68699, 2022, doi: https://doi.org/10.1109/ACCESS.2022.3185747.
[23] A. Jahani, K. Zare, and L. M. Khanli, “Short-term load forecasting for microgrid energy management system using hybrid SPM-LSTM,” Sustain. Cities Soc., vol. 98, Art. no. 104775, 2023, doi: https://doi.org/10.1016/j.scs.2023.104775.
[24] K. Park, J. Yim, H. Lee, M. Park, and H. Kim, “Real-time solar power estimation through rnn-based attention models,” IEEE Access, vol. 12, pp. 62502–62510, 2024, doi: https://doi.org/10.1109/ACCESS.2023.3233951.
[25] S. Hochreiter and J. Schmidhuber, “Long Short-term Memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, Dec. 1997, doi: https://doi.org/10.1162/neco.1997.9.8.1735.
[26] J. Silva-Rodriguez, E. Raffoul, and X. Li, “LSTM-based net load forecasting for wind and solar power-equipped microgrids,” in Proc. 2024 56th North American Power Symp. (NAPS), 2024, pp. 1–6, doi: https://doi.org/10.1109/NAPS61145.2024.10741801
[27] T.-P. Nguyen, “Predicting three-phase load demand in the smart solar microgrid with Bi-Long short-term memory,” Int. J. Parallel, Emergent Distrib. Syst., pp. 1–23, 2025, doi: https://doi.org/10.1080/17445760.2025.2602172.
[28] M. Xia, H. Shao, X. Ma, and C. W. De Silva, “A stacked GRU-RNN-based approach for predicting renewable energy and electricity load for smart grid operation,” IEEE Trans. Ind. Informatics, vol. 17, no. 10, pp. 7050–7059, 2021, doi: https://doi.org/10.1109/TII.2021.3056867.
[29] M. Sajjad et al., “A novel CNN-GRU-based hybrid approach for short-term residential load forecasting,” IEEE Access, vol. 8, pp. 143759–143768, 2020, doi: https://doi.org/10.1109/ACCESS.2020.3009537.
[30] R. Dey and F. M. Salem, “Gate-variants of gated recurrent unit (GRU) neural networks,” in Proc. 2017 IEEE 60th Midwest Symp. Circuits and Systems (MWSCAS), 2017, pp. 1597–1600, doi: https://doi.org/10.1109/MWSCAS.2017.8053243.
[31] A. Rai, A. Shrivastava, and K. C. Jana, “A robust auto encoder-gated recurrent unit (AE-GRU)-based deep learning approach for short-term solar power forecasting,” Optik, vol. 252, Art. no. 168515, 2022, doi: https://doi.org/10.1016/j.ijleo.2021.168515.
[32] J. Chen, H. Jing, Y. Chang, and Q. Liu, “Gated recurrent unit based recurrent neural network for remaining useful life prediction of nonlinear deterioration process,” Reliab. Eng. Syst. Saf., vol. 185, pp. 372–382, 2019, doi: https://doi.org/10.1016/j.ress.2019.01.006.
[33] J. Chung, C. Gulcehre, K. Cho, and Y. Bengio, “Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling,” Dec. 2014, doi: https://doi.org/10.48550/arXiv.1412.3555.
[34] M. Feurer and F. Hutter, “Hyperparameter optimization,” in Automated machine learning, Springer, Cham, 2019, pp. 3–33, doi: https://doi.org/10.1007/978-3-030-05318-5_1.
