Academic Journal of Computing & Information Science, 2024, 7(8); doi: 10.25236/AJCIS.2024.070806.
Ruotong Qiu1, Zhengxin Su2
1School of Sciences of SWPU, Southwest Petroleum University, Nanchong, 637001, China
2College of Electronic Engineering, Chengdu University of Information Technology, Chengdu, 610225, China
At present, China's traditional fossil energy is gradually depleted. Among the many new energy sources, solar energy has the advantages of abundant resources and low cost, so photovoltaic power generation has been vigorously promoted and widely used in the world. However, due to the influence of geographical environment, meteorological factors and equipment characteristics, photovoltaic power generation has the characteristics of randomness, fluctuation and anti-peak regulation, which brings many adverse effects to the normal operation and planning of the power system. In order to improve the prediction accuracy of photovoltaic power generation, a CNN-LSTM convolutional neural network prediction model is proposed, which uses a variety of convolution kernels to effectively fuse multiple feature signals to generate higher-level effective features. Taking the dataset as input, the data is filtered through the upper CNN network part, and then the filtered data is mapped to the LSTM long-term and short-term memory neural network part to achieve continuous prediction. Experiments show that the prediction results have high accuracy and stability.
Photovoltaic Power Generation Prediction, CNN, LSTM, Deep Learning
Ruotong Qiu, Zhengxin Su. Research on Photovoltaic Power Generation Forecasting Based on a Combined CNN-LSTM Neural Network Model. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 8: 33-41. https://doi.org/10.25236/AJCIS.2024.070806.
[1] Duan Wenyu, Dai Meikui, Liu Xingyan. Analysis and prediction of influencing factors of solar irradiance in photovoltaic power generation: A case study of Zhangbei County, Hebei Province.[J]. Energy saving and environmental protection. 2024(05):48-55.
[2] Chen Yun, Liu Jilei, Liu Bei, et al. Time-based prediction of photovoltaic power generation system based on uncertain weather data. [J]. China test. 2023,49(S2):76-83.
[3] Li Hanzhang, Feng Jiangtao, Wang Pengcheng, et al. Research on Photovoltaic Power Generation Prediction Model Based on TDE-SO-AWM-GRU.[J/OL] China Power. 1-10[2024-05-29].
[4] Qiu Shuqi, Jian Zhaomin, Fang Lixiong, et al. Photovoltaic power generation prediction based on variational mode decomposition and ensemble learning. [J]. Smart electricity. 2024, 52 (03): 32-38.
[5] Li Zheng, Zhang Jie, Xu Ruosi, et al. Short-term PV power prediction based on similar daily clustering and PCC-VMD-SSA-KELM model. [J]. Acta Solaria Sinica. 2024, 45 (02): 460-468.
[6] Fu Xiaobiao, Hou Jiaqi, Li Baoju, et al. A two-modal weather typing method and its application in photovoltaic power probability prediction. [J]. Power generation technology. 2024, 45 (02): 299-311.
[7] Guo Jialin, Zhi Min, Yin Yanjun, et al. A review of the hybrid model of CNN and visual Transformer in image processing. [J/OL]. Computer Science and Exploration. 1-18[2024-06-01].
[8] Wang Tao, Li Wei, Xu Ye, et al. Research on the prediction model of VMD-FE-LSTM photovoltaic output combination considering similar days. [J]. Acta Solaria Sinica. 2024, 45 (05): 490-499.
[9] Zhou Xiang, Zhang Shiming, Su Linpeng, et al. Monthly precipitation prediction based on attention mechanism and LSTM-CCN. [J/OL]. People's Yangtze River. 1-9[2024-06-01].
[10] Lv Haifeng, Tu Jingxian, Lin Hongquan, et al. Hybrid Water Level Prediction Model Based on CNN-LSTM-Attention and Auto-Regressive [J/OL]. Water Conservancy and Hydropower Technology. 1-19[2024-06-01].
[11] He Linjing, Chen Xiaolin, Zhu Linsen, et al. Risk Prediction of Digital Transformation of Cross-border Agricultural Product Supply Chain Based on PCA-BP Neural Network. [J]. Technology Entrepreneurship Monthly. 2024, 37 (05): 68-73.