基于Attention-GRU的短期光伏发电功率预测

刘国海; 孙文卿; 吴振飞; 陈兆岭; 左致远

doi:10.19912/j.0254-0096.tynxb.2020-1202

PDF(1773 KB)

太阳能学报 ›› 2022, Vol. 43 ›› Issue (2) : 226-232. DOI: 10.19912/j.0254-0096.tynxb.2020-1202

基于Attention-GRU的短期光伏发电功率预测

刘国海¹, 孙文卿¹, 吴振飞², 陈兆岭¹, 左致远¹

作者信息 +

SHORT-TERM PHOTOVOLTAIC POWER FORECASTING BASED ON ATTENTION-GRU MODEL

Liu Guohai¹, Sun Wenqing¹, Wu Zhenfei², Chen Zhaoling¹, Zuo Zhiyuan¹

Author information +

文章历史 +

摘要

针对传统长短时记忆神经网络（LSTM）参数量较多以及在处理长时间序列时容易忽略重要时序信息的不足,提出一种结合注意力机制（attention）与门控循环单元（GRU）的Attention-GRU短期光伏发电功率预测模型。首先,基于改进相似日理论建立新的数据集;然后,利用门控循环单元提取光伏发电功率的时序特征,引入注意力机制加强对时序输入中重要信息的关注;最终构建针对不同天气类型的预测模型。仿真结果表明,提出的模型与对比模型相比,预测精度更高。

Abstract

In view of the large number of parameters of traditional long-short term memory neural network （LSTM） and lack of important timing information when processing long-term sequences, an Attention-GRU short-term photovoltaic power forecasting model combining attention mechanism and gated recurrent unit （GRU） is proposed. Firstly, a forecasting model for different weather types is established. Then, GRU is used to extract the time series characteristics of photovoltaic power generation and the attention mechanism is introduced to strengthen the attention to important information in the time series input. Finally, a forecasting model for different weather types is established. Simulation results show that the proposed Attention-GRU model has higher forecasting accuracy than the comparison models.

导出引用

刘国海, 孙文卿, 吴振飞, 陈兆岭, 左致远. 基于Attention-GRU的短期光伏发电功率预测[J]. 太阳能学报. 2022, 43(2): 226-232 https://doi.org/10.19912/j.0254-0096.tynxb.2020-1202

Liu Guohai, Sun Wenqing, Wu Zhenfei, Chen Zhaoling, Zuo Zhiyuan. SHORT-TERM PHOTOVOLTAIC POWER FORECASTING BASED ON ATTENTION-GRU MODEL[J]. Acta Energiae Solaris Sinica. 2022, 43(2): 226-232 https://doi.org/10.19912/j.0254-0096.tynxb.2020-1202

中图分类号： TM615

参考文献

[1] 张倩, 马愿, 李国丽, 等. 频域分解和深度学习算法在短期负荷及光伏功率预测中的应用[J]. 中国电机工程学报, 2019, 39(8): 2221-2230, 5.
ZHANG Q, MA Y, LI G L, et al.Applications of frequency domain decomposition and deep learning algorithms in short-term load and photovoltaic power forecasting[J]. Proceedings of the CSEE, 2019, 39(8): 2221-2230, 5.
[2] 赵书强, 张婷婷, 李志伟, 等. 基于数值特性聚类的日前光伏出力预测误差分布模型[J]. 电力系统自动化, 2019, 43(13): 36-48.
ZHAO S Q, ZHANG T T, LI Z W, et al.Distribution model of day-ahead photovoltaic power forecasting error based on numerical characteristic clustering[J]. Automation of electric power systems, 2019, 43(13): 36-48.
[3] 叶林, 陈政, 赵永宁, 等. 基于遗传算法—模糊径向基神经网络的光伏发电功率预测模型[J]. 电力系统自动化, 2015, 39(16): 16-22.
YE L, CHEN Z, ZHAO Y N, et al.Photovoltaic power forecasting model based on genetic algorithm and fuzzy radial basis function neural network[J]. Automation of electric power systems, 2015, 39(16): 16-22.
[4] CHENG X, CHEN F R, YU B X, et al.The method for photovoltaic module temperature ultra-short-term forecasting based on RBF neural network[C]//China International Conference on Electricity Distribution, Xi'an, China, 2016: 1-5.
[5] 王育飞, 付玉超, 孙路, 等. 基于混沌-RBF神经网络的光伏发电功率超短期预测模型[J]. 电网技术, 2018, 42(4): 1110-1116.
WANG Y F, FU Y C, SUN L, et al.Ultra-short term prediction model of photovoltaic output power based on chaos-RBF neural network[J]. Power system technology, 2018, 42(4): 1110-1116.
[6] SHI J, LEE W J, LIU Y Q, et al.Forecasting power output of photovoltaic systems based on weather classification and support vector machines[J]. IEEE transactions on industry applications, 2012, 48(3): 1064-1069.
[7] 朱想, 丁云龙, 郭力, 等. 基于改进NARX神经网络算法的光伏发电功率短期预测[J]. 武汉大学学报(理学版), 2020, 66(5): 505-511.
ZHU X, DING Y L, GUO L, et al.Short-term forecast for photovoltaic power generation based on improved NARX neural network algorithm[J]. Journal of Wuhan University(natural science edition), 2020, 66(5): 505-511.
[8] LI Y L, SU Y, SHU L J.An ARMAX model for forecasting the power output of a grid connected photovoltaic system[J]. Renewable energy, 2014, 66: 78-89.
[9] 赵滨滨, 王莹, 王彬, 等. 基于ARIMA时间序列的分布式光伏系统输出功率预测方法研究[J]. 可再生能源, 2019, 37(6): 820-823.
ZHAO B B, WANG Y, WANG B, et al.Photovoltaic power prediction in distribution network based on ARIMA model time series[J]. Renewable energy resources, 2019, 37(6): 820-823.
[10] 杨春熙, 韩威, 高志球. 基于GRU神经网络的太阳辐照度短期预测[J]. 中国科技论文, 2020, 15(1): 8-14.
YANG C X, HAN W, GAO Z Q.Short-term forecasting for solar irradiance using GRU neural network[J]. China sciencepaper, 2020, 15(1): 8-14.
[11] 张娜, 王守相, 葛磊蛟, 等. 一种光伏短期出力区间预测方法[J]. 太阳能学报, 2020, 41(8): 173-179.
ZHANG N, WANG S X, GE L J, et al.A photovoltaic system short-term power interval forecasting method[J]. Acta energiae solaris sinica, 2020, 41(8): 173-179.
[12] 马磊, 黄伟, 李克成, 等. 基于Attention-LSTM的光伏超短期功率预测模型[J]. 电测与仪表, 2021, 58(2): 146-152.
MA L, HUANG W, LI K C, et al.Photovoltaic ultra short-term power forecating model based on Attention-GRU[J]. Electrical measurement and instrumentation, 2021, 58(2): 146-152.
[13] MESNIL G, DAUPHIN Y, YAO K S, et al.Using recurrent neural networks for slot filling in spoken language understanding[J]. IEEE/ACM transactions on audio, speech, and language processing, 2015, 23(3): 530-539.
[14] MOU L C, GHANISI P, ZHU X X.Deep recurrent neural networks for hyperspectral image classification[J]. IEEE transactions on geoscience and remote sensing, 2017, 55(7): 3639-3655.
[15] HOCHREITER S, SCHMIDHUBER J.Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.
[16] GAO M Y, ZHANG N, SHEN S L, et al.Real-time dynamic earth-pressure regulation model for shield tunneling by integrating GRU deep learning method with GA optimization[J]. IEEE access, 2020, 8: 64310-64323.
[17] CHUNG J Y, GULCEHRE C, CHO K H, et al. Empirical evaluation of gated recurrent neural network on sequence modeling[EB/OL]. http:// arxiv.org/pdf/1412.3555.pdf: 2020-07-28.
[18] LONG H, ZHANG Z J, SU Y.Analysis of daily solar power prediction with data-driven approaches[J]. Applied energy, 2014, 126: 29-37.