Dung beetle optimization algorithm-based hybrid deep learning model for ultra-short-term PV power prediction

Rui Quan; Zhizhuo Qiu; Hang Wan; Zhiyu Yang; Xuerong Li

doi:10.1016/j.isci.2024.111126

Dung beetle optimization algorithm-based hybrid deep learning model for ultra-short-term PV power prediction

iScience. 2024 Oct 11;27(11):111126. doi: 10.1016/j.isci.2024.111126. eCollection 2024 Nov 15.

Authors

Rui Quan^{1

2}, Zhizhuo Qiu^{1

2}, Hang Wan^{1

2}, Zhiyu Yang^{1

2}, Xuerong Li^{1

2}

Affiliations

¹ Hubei Key Laboratory for High-efficiency Utilization of Solar Energy and Operation Control of Energy Storage System, Hubei University of Technology, Wuhan 430068, China.
² Hubei Engineering Research Center for Safety Monitoring of New Energy and Power Grid Equipment, Hubei University of Technology, Wuhan 430068, China.

Abstract

A hybrid model combining self-attention temporal convolutional networks (SATCN) with bidirectional long short-term memory (BiLSTM) networks was developed to improve the accuracy of ultra-short-term photovoltaic (PV) power prediction. The self-attention mechanism and SATCN were used to extract temporal and correlation features, which were then linked to BiLSTM networks. The model's hyperparameters were optimized using the dung beetle optimization algorithm. The model was tested on a year-long dataset of PV power and outperformed convolutional neural networks, BiLSTM networks, temporal convolutional networks, and other hybrid models. It reduced the root-mean-square error (RMSE) by 33.1% compared to the other models. The model achieved a mean absolute error (MAE) of 0.175, a weighted mean absolute percentage error (wMAPE) of 4.821, and a coefficient of determination (R2) of 0.997. These results highlight the model's superior accuracy and its potential applications in solar energy development.

Keywords: Artificial intelligence; Energy Modelling; Engineering.