With the spatial and temporal characteristics of solar irradiance such as intermittency and nonlinearity
the prediction accuracy has a significant impact on the optimal operation of multi-energy cooperative heating systems. To address the problems of the existing machine learning prediction algorithms
such as the difficulty of hyper-parameter optimization and the insufficient accuracy to meet the demand of optimization and regulation
a solar irradiance prediction model based on the dung beetle optimized temporal convolutional network (DBO-TCN) is proposed. The model utilizes the TCN temporal convolutional network to effectively integrate the parallel processing capability of the convolutional neural network and the temporal modeling function of the recurrent neural network. The hyperparameters of TCN are optimized by simulating the dung beetle habit swarm intelligent optimization algorithm
which more accurately exploits the spatiotemporal evolution law of solar irradiance. Detailed comparison experiment results with state-of-the-art algorithms such as TCN and LSTM show that the proposed solar radiation prediction model based on DBO-TCN demonstrates superior prediction accuracy and robustness.
XIE Y, YANG J, SENGUPTA M, et al.Improving the prediction of DNI with physics-based representation of all-sky circumsolar radiation[J]. Solar energy, 2022, 231: 758-766.
RODRÍGUEZ-BENÍTEZ F J, LÓPEZ-CUESTA M, ARBIZU-BARRENA C, et al. Assessment of new solar radiation nowcasting methods based on sky-camera and satellite imagery[J]. Applied energy, 2021, 292: 116838.
OLATOMIWA L, MEKHILEF S, SHAMSHIRBAND S, et al.A support vector machine-firefly algorithm-based model for global solar radiation prediction[J]. Solar energy, 2015, 115: 632-644.
JOVIĆ S, ANIČIĆ O, MARSENIĆ M, et al. Solar radiation analyzing by neuro-fuzzy approach[J]. Energy and buildings, 2016, 129: 261-263.
GHIMIRE S, DEO R C, RAJ N, et al.Deep solar radiation forecasting with convolutional neural network and long short-term memory network algorithms[J]. Applied energy, 2019, 253: 113541.
WANG P, XUE B, LIANG J, et al.Feature clustering-assisted feature selection with differential evolution[J]. Pattern recognition, 2023, 140: 109523.
XUE J K, SHEN B.Dung beetle optimizer: a new meta-heuristic algorithm for global optimization[J]. The journal of supercomputing, 2023, 79(7): 7305-7336.