Distributed Photovoltaic Power Energy Generation Prediction Based on Improved Multi-objective Particle Algorithm

Yuanzheng Xiao; Huawei Hong; Feifei Chen; Xiaorui Qian; Ming Xu; Hanbin Ma

doi:10.4108/ew.8901

Authors

Yuanzheng Xiao State Grid Fujian Marketing Service Center
Huawei Hong State Grid Fujian Marketing Service Center
Feifei Chen State Grid Fujian Marketing Service Center
Xiaorui Qian State Grid Fujian Marketing Service Center
Ming Xu State Grid Fujian Marketing Service Center
Hanbin Ma State Grid Info-Telecom Great Power Science and Technology Co Ltd

DOI:

https://doi.org/10.4108/ew.8901

Keywords:

Particle Algorithm, Distributed photovoltaic power generation, Power prediction, Long short-term memory network, Intelligent Power Grid

Abstract

Accurate prediction of distributed photovoltaic (DPV) power generation is crucial for stable grid operation, yet existing methods struggle with the non-linear, intermittent nature of solar power, and traditional machine learning models face hyperparameter selection and overfitting challenges. This study developed a highly accurate DPV power prediction method by optimizing a Long Short-Term Memory (LSTM) network's hyperparameters using an improved Multi-Objective Particle Swarm Optimization (MO-PSO) algorithm. A hybrid LSTM-PSO model was created, where the LSTM network served as the core prediction model, and the improved MO-PSO algorithm optimized its hyperparameters, enhancing generalization and avoiding overfitting. The LSTM-PSO model significantly improved prediction accuracy compared to traditional methods. Key results from two power stations included a maximum deviation of 6.2 MW at Power Station A, a peak time deviation of less than 0.1 MW at Power Station B, and a prediction interval error controlled below 30 MW at an 80% confidence level. The optimized LSTM-PSO model effectively captures DPV power generation dynamics, and the superior performance metrics demonstrate its potential for intelligent grid management. However, limitations include prediction accuracy under extreme weather and computational efficiency for large datasets. Future work will focus on broader applicability and more efficient algorithm variants.

Downloads

References

[1] Y. Wang, W. Fu, X. Zhang, Z. Zhen, and F. Wang, "Dynamic directed graph convolution network based ultra-short-term forecasting method of distributed photovoltaic power to enhance the resilience and flexibility of distribution network," IET Generation, Transmission & Distribution, vol. 18, no. 2, pp. 337-352, Sep. 2024. DOI: 10.1049/gtd2.12963.

[2] W. C. Tsai, C. S. Tu, C. M. Hong, and W. Lin, "A review of state-of-the-art and short-term forecasting models for solar PV power generation," Energies, vol. 16, no. 14, pp. 5436-5466, Jul. 2023. DOI: 10.3390/en16145436.

[3] E. M. Al-Ali, Y. Hajji, Y. Said, et al., "Solar energy production forecasting based on a hybrid CNN-LSTM-transformer model," Mathematics, vol. 11, no. 3, pp. 676-698, Jan. 2023. DOI: 10.3390/math11030676.

[4] J. L. J. Pereira, G. A. Oliver, and M. B. Francisco, "A review of multi-objective optimization: methods and algorithms in mechanical engineering problems," Archives of Computational Methods in Engineering, vol. 29, no. 4, pp. 2285-2308, Jun. 2022. DOI: 10.1007/s11831-021-09663-x.

[5] B. Abdollahzadeh and F. S. Gharehchopogh, "A multi-objective optimization algorithm for feature selection problems," Engineering with Computers, vol. 38, suppl. 3, pp. 1845-1863, Aug. 2022. DOI: 10.1007/s00366-021-01369-9.

[6] Y. Xu, C. Xu, H. Zhang, L. Huang, Y. Liu, Y. Nojima, et al., "A multi-population multi-objective evolutionary algorithm based on the contribution of decision variables to objectives for large-scale multi/many-objective optimization," IEEE Transactions on Cybernetics, vol. 53, no. 11, pp. 6998-7007, Nov. 2022. DOI: 10.1109/TCYB.2022.3180214.

[7] L. Hu, Y. Yang, Z. Tang, Y. He, and X. Luo, "FCAN-MOPSO: an improved fuzzy-based graph clustering algorithm for complex networks with multiobjective particle swarm optimization," IEEE Transactions on Fuzzy Systems, vol. 31, no. 10, pp. 3470-3484, Mar. 2023. DOI: 10.1109/TFUZZ.2023.3259726.

[8] M. Suresh, R. Meenakumari, H. Panchal, V. Priya, E. Agouz, and M. Israr, "An enhanced multiobjective particle swarm optimisation algorithm for optimum utilisation of hybrid renewable energy systems," International Journal of Ambient Energy, vol. 43, no. 1, pp. 2540-2548, Apr. 2022. DOI: 10.1080/01430750.2020.1737837.

[9] P. Kahhal, M. Ghasemi, M. Kashfi, G. Hossein, and J. Kim, "A multi-objective optimization using response surface model coupled with particle swarm algorithm on FSW process parameters," Scientific Reports, vol. 12, no. 1, pp. 2837-2857, Feb. 2022. DOI: 10.1038/s41598-022-06652-3.

[10] I. Rahimi, A. H. Gandomi, F. Chen, and E. Montes, "A review on constraint handling techniques for population-based algorithms: from single-objective to multi-objective optimization," Archives of Computational Methods in Engineering, vol. 30, no. 3, pp. 2181-2209, Apr. 2023. DOI: 10.1007/s11831-022-09859-9.

[11] L. Ge, T. Du, C. Li, Y. Li, J. Yan, and M. Rafiq, "Virtual collection for distributed photovoltaic data: Challenges, methodologies, and applications," Energies, vol. 15, no. 23, pp. 8783-8807, Nov. 2022. DOI: 10.3390/en15238783.

[12] K. J. Iheanetu, "Solar photovoltaic power forecasting: A review," Sustainability, vol. 14, no. 24, pp. 17005-17036, Dec. 2022. DOI: 10.3390/su142417005.

[13] M. N. Akhter, S. Mekhilef, H. Mokhlis, Z. Almohaimeed, A. Muhammad, A. Khairuddin, et al., "An hour-ahead PV power forecasting method based on an RNN-LSTM model for three different PV plants," Energies, vol. 15, no. 6, pp. 2243-2264, Mar. 2022. DOI: 10.3390/en15062243.

[14] M. AlKandari and I. Ahmad, "Solar power generation forecasting using ensemble approach based on deep learning and statistical methods," Applied Computing and Informatics, vol. 20, no. 3/4, pp. 231-250, Jun. 2024. DOI: 10.1016/j.aci.2019.11.002.

[15] W. Zhang, X. Chen, and K. He, "Semi-asynchronous personalized federated learning for short-term photovoltaic power forecasting," Digital Communications and Networks, vol. 9, no. 5, pp. 1221-1229, Oct. 2023. DOI: 10.1016/j.dcan.2022.03.022.

[16] S. M. Miraftabzadeh, C. G. Colombo, and M. Longo, "A day-ahead photovoltaic power prediction via transfer learning and deep neural networks," Forecasting, vol. 5, no. 1, pp. 213-228, Feb. 2023. DOI: 10.3390/forecast5010012.

[17] N. Khodadadi, F. S. Gharehchopogh, and S. Mirjalili, "MOAVOA: a new multi-objective artificial vultures optimization algorithm," Neural Computing and Applications, vol. 34, no. 23, pp. 20791-20829, Dec. 2022. DOI: 10.1007/s00521-022-07557-y.

[18] P. Jangir, H. Buch, S. Mirjalili, and P. Manoharan, "MOMPA: Multi-objective marine predator algorithm for solving multi-objective optimization problems," Evolutionary Intelligence, vol. 16, no. 1, pp. 169-195, Feb. 2023. DOI: 10.1007/s12065-021-00649-z.