Distributed photovoltaic power prediction considering spatiotemporal correlation and dual Attention-LSTM

Yueyuan Zhang; Yifan Zhang; Dazhi Pan; Mingyu Sun; Huawei Mei; Wangbin Cao

doi:10.4108/ew.7530

Authors

Yueyuan Zhang Inner Mongolia Power (Group) Co., Ltd.
Yifan Zhang Inner Mongolia Electric Power Research Institute
Dazhi Pan Inner Mongolia Power (Group) Co., Ltd.
Mingyu Sun North China Electric Power University
Huawei Mei North China Electric Power University
Wangbin Cao North China Electric Power University

DOI:

https://doi.org/10.4108/ew.7530

Keywords:

Distributed Photovoltaic, Power Prediction, Feature Fusion, K-means Algorithm, Attention-LSTM Model

Abstract

Predicting the power output of photovoltaic clusters is crucial for optimizing regional solar power scheduling. To enhance the accuracy of distributed photovoltaic station power forecasts, a method incorporating spatiotemporal correlation and dual Attention-LSTM is introduced. The K-means algorithm is first employed to classify the distributed photovoltaic power station clusters in the area. The reference station for the target photovoltaic station is determined by calculating the Euclidean distance between the target station and the typical daily power profiles of other stations in the cluster. Simultaneously, pivotal weather features that influence photovoltaic output are ascertained through computation of the Pearson correlation coefficient. Subsequently, an Attention-LSTM-based power prediction and error correction model is constructed, utilizing both meteorological and power traits as input variables to finalize the photovoltaic power generation forecast. To validate the approach, a simulation analysis is conducted using empirical data from Arizona, USA. The experimental results indicate that the suggested method greatly improves the accuracy of predictions for distributed photovoltaic power.

Downloads

Download data is not yet available.

References

[1] XIN Baoan, SHAN Baoguo, LI Qionghui, et al. Rethinking of the “Three Elements of Energy” Toward Carbon Peak and Carbon Neutrality[J]. Proceedings of the CSEE, 2022,42(09):3117-3126.

[2] ARGUELLO A, LARA J D, ROJAS J D, et al. Impact of rooftop PV integration in distribution systems considering socioeconomic factors[J]. IEEE Systems Journal, 2017, 12(4): 3531-3542. DOI: https://doi.org/10.1109/JSYST.2017.2739022

[3] SONG Shaojian, LI Bohan. Short-term forecasting method of photovoltaic power based on LSTM[J]. Renewable Energy,2021,39(05):594-602.

[4] TIAN Jiangang. Ultra short-term forecast of photovoltaic generation based on gru of deep learning algorithm[D]. East China Jiao Tong University,2021.

[5] WEN S, ZHANG C, LAN H, et al. A hybrid ensemble model for interval prediction of solar power output in ship onboard power systems[J]. IEEE Transactions on Sustainable Energy, 2019, 12(1): 14-24. DOI: https://doi.org/10.1109/TSTE.2019.2963270

[6] ABDEL-NASSER M, MAHMOUD K, LEHTONEN M. Reliable solar irradiance forecasting approach based on choquet integral and deep LSTMs[J]. IEEE Transactions on Industrial Informatics, 2020, 17(3): 1873-1881. DOI: https://doi.org/10.1109/TII.2020.2996235

[7] TANG Deqing,ZHU Wu,HOU Linchao. Ultra-short-term photovoltaic power prediction based on cnn-lstm-xgboost model[J]. Chinese Journal of Power Sources,2022,46(09):1048-1052.

[8] LIU Zhichao,YUAN,SannanTANG Wancheng. Output power prediction of short-term photovoltaic power generation based on BLSTM-random forest[J]. Chinese Journal of Power Sources, 2021,45(04):495-498.

[9] YU Guangzheng, LU Liu, TANG Bo, et al. An Improved Hybrid Neural Network Ultra-Short-Term Photovoltaic Power Forecasting Method Based On Cloud Image Feature Extraction[J]. Proceedings of the CSEE, 2021,41(20):6989-7003.

[10] ZHOU H, ZHANG Y, YANG L, et al. Short-term photovoltaic power forecasting based on long short term memory neural network and attention mechanism[J]. Ieee Access, 2019, 7: 78063-78074. DOI: https://doi.org/10.1109/ACCESS.2019.2923006

[11] QI Xiaoxia. Research on photovoltaic/wind power forecasting based on deep learning[D]. Harbin Engineering University,2020.

[12] ZHENG Ruonan, LI Guojie, HAN Bei, et al. ay-ahead power forecasting of distributed photovoltaic generation based on weighted expanded daily feature matrix[J]. Electric Power Automation Equipment,2022,42(02):99-105

[13] WANG Biao, LYU Yang, CHEN Zhong, et al. Hybrid mechanism-data-driven short-term power forecasting of distributed photovoltaic considering information time shift [J]. Automation of Electric Power Systems,2022,46(11):67-74.

[14] ZHANG Tongyan, LIAO Qingfen, TANG Fei, et al. Wide-area distributed photovoltaic power forecast method based on meteorological resource interpolation and transfer learning[J/OL]. IEEE Systems Journal:1-12[2023-07-22]

[15] MIRJALILI S, MIRJALILI S M, HATAMLOUq A. Multi-verse optimizer: a nature-inspired algorithm for global optimization[J]. Neural Computing and Applications, 2016, 27: 495-513. DOI: https://doi.org/10.1007/s00521-015-1870-7

[16] JIAO Tianli. Study on key models of wide area distributed photovoltaic power generation output prediction based on spatio-temporal relationship[D]. Hangzhou Dianzi University,2019.

[17] YANG Xiyun, ZHAO Zeyu, YANG Yan. Research on distributed photovoltaic power prediction method based on combination of spatiotemporal information[J]. Thermal Power Generation,2022,51(08):64-72.

[18] WANG Hao. Reliability evaluation of power generation systems with high-proportion of renewable energy[D]. North China Electric Power University,2020.

[19] FANG Hui. Optimization planning and application research of high penetrated distributed photovoltaic generation cluster[D]. Hefei University of Technology,2019.

[20] WANG Xiaoxia, YU Min, HUO Zejian, et al. Short-term power forecasting of distributed photovoltaic station clusters based on affinity propagation clustering and long short-term time-series network[J]. Automation of Electric Power Systems, 2023,47(06):133-141.

[21] WANG Kaiyan, DU Haodong, JIA Rong, et al. Short-term interval probability prediction of photovoltaic power based on similar daily clustering and QR-CNN-BiLSTM model[J]. High Voltage Technology,2022,48(11):4372-4388.

[22] YANG Guohua,, ZHANG Honghao, ZHENG Haofeng. Short-term photovoltaic power forecasting based on similar weather clustering and IHGWO-WNN-AdaBoost model[J]. High Voltage Technology, 2021,47(04):1185-1194.

[23] LIU Guohai, SUN Wenqing, WU Zhenfei, et al. Short-term photovoltaic power forecasting based on Attention-GRU model[J]. Journal of Solar Energy,2022,43(02):226-232.

[24] BAN Lan. Research on short-term photovoltaic power prediciton based on long short memory neural network[D]. Guangxi Universiy,2021.