为有效挖掘光伏发电功率数据中的有效时序信息,进一步提升光伏发电功率预测效果,提出一种基于多因素融合的高效通道注意力机制（ECA）-时间卷积网络（TCN）预测模型。首先,采用最大互信息系数（MIC）提取光伏发电功率相关特征;其次,使用多项式特征衍生方法融合各相关因素特征,衍生高维特征,进行特征组合;然后,将自适应选择一维卷积核大小的ECA模块与可有效捕捉光伏发电功率数据时序性信息的TCN相结合,搭建ECA-TCN预测模型;最后,采用多个模型进行对比实验。实验结果表明：该文提出的特征组合方法可高效的选择光伏发电功率数据特征,提升特征的表现能力。特征组合后的 ECA-TCN预测模型的均方根误差（RMSE）为0.0828 kW,相较于LSTM、LSTM-TCN、ECA-LSTM,ECA-TCN的RMSE分别降低了0.29、0.23和0.13个百分点,并具有最优的拟合度（R2）90.74%。该模型可在保持高拟合度的同时有效提高光伏发电功率预测精度。
Abstract
To effectively extract valuable temporal information from photovoltaic （PV） power data and further improve the accuracy of PV power prediction, we propose an efficient channel attention mechanism （ECA）- temporal convolutional network （TCN） prediction model based on multi-factor fusion. Firstly, the maximum information coefficient （MIC） is utilized to extract relevant features of PV power. Secondly, a polynomial feature derivation method is employed to combine the features of various factors, generating high-dimensional features and facilitating feature combination. Then, the ECA module, which adaptively selects the size of one-dimensional convolutional kernels, is combined with TCN to construct the ECA-TCN prediction model, which effectively captures the temporal characteristics of PV power data. Finally, multiple models are compared through experimental evaluation. The results demonstrate that the proposed feature combination method efficiently selects PV power data features and enhances their discriminative ability. The ECA-TCN prediction model with feature combination achieves a root mean square error （RMSE） of 0.0828 kW. Compared to LSTM, LSTM-TCN, and ECA-LSTM, the RMSE of the ECA-TCN was reduces by 0.29, 0.23, and 0.13 percentage points, respectively, and exhibits the best fitting performance with an R2 value of 90.74%. This model effectively improves the accuracy of PV power prediction while maintaining a high fitting performance.
关键词
光伏发电 /
预测 /
时间卷积网络 /
最大互信息系数 /
高效通道注意力
Key words
PV power /
forecasting /
temporal convolutional network /
max information coefficient /
efficient channel attention
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] HONG T, PINSON P, WANG Y, et al.Energy forecasting: a review and outlook[J]. IEEE open access journal of power and energy, 2020, 7: 376-388.
[2] LAW E W, PRASAD A A, KAY M, et al.Direct normal irradiance forecasting and its application to concentrated solar thermal output forecasting-a review[J]. Solar energy, 2014, 108: 287-307.
[3] BENMOUIZA K, CHEKNANE A.Small-scale solar radiation forecasting using ARMA and nonlinear autoregressive neural network models[J]. Theoretical and applied climatology, 2016, 124(3): 945-958.
[4] 李桂兰, 杨杰, 周满国. 基于改进时间卷积网络的光伏发电功率预测[J]. 激光与光电子学进展, 2022, 59(8): 480-489.
LI G L, YANG J, ZHOU M G.Power prediction of photovoltaic generation based on improved temporal convolutional network[J]. Laser & optoelectronics progress, 2022, 59(8): 480-489.
[5] 武新章, 王泽宇, 代伟, 等. 基于异质聚类与Stacking的双集成光伏发电功率预测[J]. 电网技术, 2023, 47(1): 275-284.
WU X Z, WANG Z Y, DAI W, et al.Bi-ensembled photovoltaic (PV) power prediction based on heterogeneous clustering and stacking[J]. Power system technology, 2023, 47(1): 275-284.
[6] 程港, 林小峰, 宋绍剑, 等. 基于PCA-GA-ELM的光伏发电功率预测研究[J]. 可再生能源, 2019, 37(10): 1440-1447.
CHENG G, LIN X F, SONG S J, et al.Research on photovoltaic power generation forecasting based on PCA-GA-ELM[J]. Renewable energy resources, 2019, 37(10): 1440-1447.
[7] 杨凌升, 李伟. 基于多气象要素降维及改进型变分模态分解算法的光伏发电功率预测模型研究[J]. 可再生能源, 2022, 40(9): 1157-1165.
YANG L S, LI W.Research on photovoltaic power prediction model based on multi-meteorological factors dimension reduction and OVMD-tSSA-LSSVM algorithm[J]. Renewable energy resources, 2022, 40(9): 1157-1165.
[8] 杨帆, 申亚, 李东东, 等. 基于GA-GNNM的极地光伏发电功率预测方法[J]. 太阳能学报, 2022, 43(4): 167-174.
YANG F, SHEN Y, LI D D, et al.Polar photovoltaic power forecasting method based on GA-GNNM[J]. Acta energiae solaris sinica, 2022, 43(4): 167-174.
[9] 商立群, 李洪波, 侯亚东, 等. 基于VMD-ISSA-KELM的短期光伏发电功率预测[J]. 电力系统保护与控制, 2022, 50(21): 138-148.
SHANG L Q, LI H B, HOU Y D, et al.Short-term photovoltaic power generation prediction based on VMD-ISSA-KELM[J]. Power system protection and control, 2022, 50(21): 138-148.
[10] YANG B, ZHU T J, CAO P L, et al.Classification and summarization of solar irradiance and power forecasting methods: a thorough review[J]. CSEE journal of power and energy systems, 2023, 9(3): 978-995.
[11] 谭海旺, 杨启亮, 邢建春, 等. 基于XGBoost-LSTM组合模型的光伏发电功率预测[J]. 太阳能学报, 2022, 43(8): 75-81.
TAN H W, YANG Q L, XING J C, et al.Photovoltaic power prediction based on combined XGBoost-LSTM model[J]. Acta energiae solaris sinica, 2022, 43(8): 75-81.
[12] 荆博. 光伏电站短期功率预测方法研究[D]. 镇江: 江苏大学, 2017.
JING B.Study on short-term power forecasting method of photovoltaic power station[D]. Zhenjiang: Jiangsu University, 2017.
[13] 蔡金锭, 叶荣, 陈汉城. 回复电压多元参数回归分析的油纸绝缘老化诊断方法[J]. 电工技术学报, 2018, 33(21): 5080-5089.
CAI J D, YE R, CHEN H C.Aging diagnosis method of oil-paper insulation based on multiple parameter regression analysis of recovery voltage[J]. Transactions of China Electrotechnical Society, 2018, 33(21): 5080-5089.
[14] 刘翼飞, 崔承刚. 基于地基云图云量特征的光伏发电功率区间预测[J]. 南方电网技术, 2023, 17(2): 92-100.
LIU Y F, CUI C G.Interval prediction for short-term solar power based on cloud features of ground-based cloud images[J]. Southern power system technology, 2023, 17(2): 92-100.
[15] 王献志, 曾四鸣, 周雪青, 等. 基于XGBoost联合模型的光伏发电功率预测[J]. 太阳能学报, 2022, 43(4): 236-242.
WANG X Z, ZENG S M, ZHOU X Q, et al.Power forecast of photovoltaic generation based on XGBoost combined model[J]. Acta energiae solaris sinica, 2022, 43(4): 236-242.
[16] 徐鹤勇, 张倩. 基于数字孪生和改进LSTM的光伏发电预测技术[J]. 热能动力工程, 2023, 38(2): 84-91, 100.
XU H Y, ZHANG Q.Photovoltaic power generation prediction technology based on digital twin and improved LSTM[J]. Journal of engineering for thermal energy and power, 2023, 38(2): 84-91, 100.
[17] LEA C, FLYNN M D, VIDAL R, et al.Temporal convolutional networks for action segmentation and detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA, 2017: 1003-1012.
[18] WANG Q L, WU B G, ZHU P F, et al.ECA-net: efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, WA, USA, 2020: 11531-11539.
[19] 刘莹, 杨超宇. 基于多因素的LSTM瓦斯浓度预测模型[J]. 中国安全生产科学技术, 2022, 18(1): 108-113.
LIU Y, YANG C Y.LSTM gas concentration prediction model based on multiple factors[J]. Journal of safety science and technology, 2022, 18(1): 108-113.
基金
国家自然科学基金（71371091）; 辽宁省社会科学规划基金（L14BTJ004）
PDF(1333 KB)
