提出一种基于双重注意力机制GRU网络（dual-attention-GRU）及相似序列修正的光伏功率预测模型。在Encoder-Decoder框架的基础上引入特征注意力以及时间注意力,能有效解决GRU网络对于输入特征及时间序列存在注意力分散的问题;采用相似功率序列的未来功率值对DA-GRU预测结果进行修正,能进一步改进预测结果。算例采用DKASC数据进行验证,对比模型在不同预测步长下的表现,结果表明：相比于其他传统模型,DA-GRU在不同评价指标下具有最佳的预测表现,且相似序列修正方法能进一步提高其预测精度。
Abstract
A photovoltaic power forecasting model based on dual-attention-GRU network and similar sequences modification is proposed. On the basis of the Encoder-Decoder framework, feature attention and temporal attention are introduced, which can effectively solve the problem of GRU network’ s distraction from input features and time series. The DA-GRU forecasting results can be further improved by using the future power values of similar power sequences to modify the forecasting results. The example is verified by DKASC data, and the performance of the model under different forecasting steps is compared. The results show that DA-GRU has the best performance under different evaluation indexes compared with other traditional models, and the similar sequences modification method can further improve its forecasting accuracy.
关键词
光伏发电 /
神经网络 /
功率预测 /
注意力机制 /
相似修正
Key words
photovoltaic power /
neural network /
power forecasting /
attention mechanism /
similarity modification
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] AHMED R, SREERAM V, MISHRA Y, et al.A review and evaluation of the state-of-the-art in PV solar power forecasting: techniques and optimization[J]. Renewable and sustainable energy reviews, 2020, 124: 109792.
[2] DOLARA A, LEVA S, MANZOLINI G.Comparison of different physical models for PV power output prediction[J]. Solar energy, 2015, 119: 83-99.
[3] AGGA A, ABBOU A, LABBADI M, et al.CNN-LSTM: an efficient hybrid deep learning architecture for predicting short-term photovoltaic power production[J]. Electric power systems research, 2022, 208: 107908.
[4] DE LA PARRA I, MUÑOZ M, LORENZO E, et al. PV performance modelling: a review in the light of quality assurance for large PV plants[J]. Renewable and sustainable energy reviews, 2017, 78: 780-797.
[5] WANG M, PENG J Q, LUO Y M, et al.Comparison of different simplistic prediction models for forecasting PV power output: assessment with experimental measurements[J]. Energy, 2021, 224: 120162.
[6] BOLAND J, DAVID M, LAURET P.Short term solar radiation forecasting: island versus continental sites[J]. Energy, 2016, 113: 186-192.
[7] NIU D X, WANG K K, SUN L J, et al.Short-term photovoltaic power generation forecasting based on random forest feature selection and CEEMD: a case study[J]. Applied soft computing, 2020, 93: 106389.
[8] 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.
[9] 魏联滨, 王彬, 王莹, 等. 基于气象相似日选取与提升回归树的光伏发电短期功率预测[J]. 电子器件, 2022, 45(1): 183-188.
WEI L B, WANG B, WANG Y, et al.Short-term power forecast of photo-voltaic power generation based on weather similarity day and boosting regression tree[J]. Chinese journal of electron devices, 2022, 45(1): 183-188.
[10] LEE D H, KIM K.PV power prediction in a peak zone using recurrent neural networks in the absence of future meteorological information[J]. Renewable energy, 2021, 173: 1098-1110.
[11] NIE Y H, ZAMZAM A S, BRANDT A.Resampling and data augmentation for short-term PV output prediction based on an imbalanced sky images dataset using convolutional neural networks[J]. Solar energy, 2021, 224: 341-354.
[12] MARKOVICS D, MAYER M J.Comparison of machine learning methods for photovoltaic power forecasting based on numerical weather prediction[J]. Renewable and sustainable energy reviews, 2022, 161: 112364.
[13] CHEN H L, CHANG X F. Photovoltaic power prediction of LSTM model based on Pearson feature selection[EB/OL].2015: arXiv:1511.04868v2. https://arxiv.org/abs/1511.04868v2.
[14] JAITLY N, LE Q V, VINYALS O, et al. An online sequence-to-sequence model using partial conditioning[J]. Computer science, 2015:DOI: 10.48550/arXiv.1511.04868.
[15] CHO K, MERRIENBOER B V, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[EB/OL]. 2014: arXiv: 1406.1078. http://arxiv.org/abs/1406.1078.pdf.
[16] FAZLIPOUR Z, MASHHOUR E, JOORABIAN M.A deep model for short-term load forecasting applying a stacked autoencoder based on LSTM supported by a multi-stage attention mechanism[J]. Applied energy, 2022, 327: 120063.
[17] DKASC: Array 3-B, 38.3 kW, mono-Si, Roof, 2016-2017,Yulara Solar System. https://dkasolarcentre.com.au/source/yulara/yulara-3-roof-sails-in-the-desert-1-1.
[18] DKASC: Array 3-C, 45.78 kW, mono-Si, Roof, 2017-2018,Yulara Solar System. https://dkasolarcentre.com.au/source/yulara/yulara-3-roof-sails-in-the-desert-1.
基金
江苏省碳达峰碳中和科技创新重点项目（BE2022027-4）
PDF(2633 KB)
