SOLAR IRRADIANCE PREDICTION ALGORITHM BASED ON DUNG BEETLE OPTIMIZED TEMPORAL CONVOLUTIONAL NETWORK

Song Jiancai; Liu Jianrong; Zhang Xinyang

doi:10.19912/j.0254-0096.tynxb.2024-0228

PDF(2238 KB)

Acta Energiae Solaris Sinica ›› 2025, Vol. 46 ›› Issue (6) : 494-500. DOI: 10.19912/j.0254-0096.tynxb.2024-0228

SOLAR IRRADIANCE PREDICTION ALGORITHM BASED ON DUNG BEETLE OPTIMIZED TEMPORAL CONVOLUTIONAL NETWORK

Song Jiancai, Liu Jianrong, Zhang Xinyang

Author information +

History +

Abstract

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.

Key words

solar irradiance / prediction algorithms / deep learning / optimization algorithm

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Song Jiancai, Liu Jianrong, Zhang Xinyang. SOLAR IRRADIANCE PREDICTION ALGORITHM BASED ON DUNG BEETLE OPTIMIZED TEMPORAL CONVOLUTIONAL NETWORK[J]. Acta Energiae Solaris Sinica. 2025, 46(6): 494-500 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0228

References

[1] 毛显强, 郭枝, 高玉冰. 碳达峰、碳中和与经济、社会、生态环境的协同研究[J]. 环境保护, 2021, 49(23): 30-35.
MAO X Q, GUO Z, GAO Y B.The synergy between carbon peak, carbon neutrality and economy, society and ecological environment[J]. Environmental protection, 2021, 49(23): 30-35.
[2] VIJAYAKUMAR G, KUMMERT M, KLEIN S A, et al.Analysis of short-term solar radiation data[J]. Solar energy, 2005, 79(5): 495-504.
[3] 刘笑, 杨丽薇, 花家嘉, 等. 晴空模型在北方地区的适用性研究: 以甘肃、河北部分地区为例[J]. 太阳能学报, 2023, 44(3): 1-7.
LIU X, YANG L W, HUA J J, et al.Research on applicability of clear-sky models in northern China: taking some regions in Hebei and Gansu as examples[J]. Acta energiae solaris sinica, 2023, 44(3): 1-7.
[4] 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.
[5] 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.
[6] 李津, 史加荣, 张琰妮, 等. 基于最大信息系数的短期太阳辐射协同估计[J]. 太阳能学报, 2023, 44(9): 286-294.
LI J, SHI J R, ZHANG Y N, et al.Short-term solar radiation synergy estimation based on maximum information coefficient[J]. Acta energiae solaris sinica, 2023, 44(9): 286-294.
[7] 张起源, 王磊, 陈天鹏, 等. 基于MLP-Garson模型的分钟尺度太阳辐照直、散射分离建模与验证研究[J]. 太阳能学报, 2023, 44(4): 531-538.
ZHANG Q Y, WANG L, CHEN T P, et al.Modeling and validation of minute-scale solar irradiance direct and diffuse separation based on MLP-Garson model[J]. Acta energiae solaris sinica, 2023, 44(4): 531-538.
[8] 于瑛, 陈笑, 贾晓宇, 等. 基于GA-BP神经网络的逐时总辐射分组模型研究[J]. 太阳能学报, 2022, 43(8): 157-163.
YU Y, CHEN X, JIA X Y, et al.Research on grouping model of hourly global solar radiation based on GA-BP neural network[J]. Acta energiae solaris sinica, 2022, 43(8): 157-163.
[9] 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.
[10] JOVIĆ S, ANIČIĆ O, MARSENIĆ M, et al. Solar radiation analyzing by neuro-fuzzy approach[J]. Energy and buildings, 2016, 129: 261-263.
[11] 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.
[12] 倪超, 王聪, 朱婷婷, 等. 基于CNN-Bi-LSTM的太阳辐照度超短期预测[J]. 太阳能学报, 2022, 43(3): 197-202.
NI C, WANG C, ZHU T T, et al.Super-short-term forecast of solar irradiance based on CNN-Bi-LSTM[J]. Acta energiae solaris sinica, 2022, 43(3): 197-202.
[13] WANG P, XUE B, LIANG J, et al.Feature clustering-assisted feature selection with differential evolution[J]. Pattern recognition, 2023, 140: 109523.
[14] 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.