针对光伏发电功率预测的LSTformer模型

doi:10.3778/j.issn.1002-8331.2301-0155

摘要/Abstract

摘要： 为了提高光伏发电功率预测精度，提出了一种基于长短期时序数据融合的Transformer生成式预测模型：LSTformer，能准确有效地预测光伏发电功率。LSTformer创新性地提出了时序分析模块（time series analysis，TSA）、时序特征融合模块（time series feature fusion，TSFF）和多周期嵌入模块（cycleEmbed），利用数据融合解决难以提取多时间尺度时序特征问题。设计时间卷积前馈（time convolution feedforward，TCNforward）单元，在编解码的过程中进一步提取时序特征。利用某光伏电站实际历史发电数据，通过实验验证LSTformer模型在光伏发电功率预测领域得到最低的均方误差（mean squared error，MSE）、平均绝对误差（mean absolute error，MAE），并通过消融实验验证了各模块的有效性。

关键词: Transformer, 长短期记忆网络, 跳跃-门控循环单元, 光伏发电功率预测, 时序数据预测

Abstract: In order to improve the prediction accuracy of photovoltaic power, a Transformer generation prediction model based on data fusion is proposed：LSTformer, which can accurately and effectively predict short-term photovoltaic power. LSTformer proposes a time series analysis (TSA) module, a time series feature fusion (TSFF) module and a cycleEmbed module. It uses data fusion to solve the problem that it is difficult to extract multiple time series features. The time convolution feedforward (TCNforward) unit is designed to further extract the timing characteristics in the process of encoding and decoding. Using the actual historical power data of a photovoltaic power station, the LSTformer model is verified to have the lowest mean squared error (MSE) and mean absolute error (MAE) in the field of photovoltaic power prediction through experiments, and the effectiveness of each module is verified through ablation experiments.

Key words: Transformer, long short term memory (LSTM), skip gated recurrent unit (skip-GRU), photovoltaic power prediction, time series data prediction

刘世鹏, 宁德军, 马崛. 针对光伏发电功率预测的LSTformer模型[J]. 计算机工程与应用, 2024, 60(9): 317-325.

LIU Shipeng, NING Dejun, MA Jue. LSTformer Model for Photovoltaic Power Prediction[J]. Computer Engineering and Applications, 2024, 60(9): 317-325.

参考文献

[1] IEA. Technology roadmap-energy storage[R/OL]. (2014-09)[2022-12-29]. https://www.iea.org/reports/technology-roadmap-energy-storage.
[2] FOLEY A M, LEAHY P G, MARVUGLIA A, et al. Current methods and advances in forecasting of wind power generation[J]. Renewable Energy, 2012, 37(1): 1-8.
[3] ZENG J, WEI Q. Short-term solar power prediction using a support vector machine[J]. Renewable Energy, 2013, 52(4): 118-127.
[4] ZAGOURAS A, PEDRO H, COIMBRA C. On the role of lagged exogenous variables and spatio-temporal correlations in improving the accuracy of solar forecasting methods[J]. Renewable Energy, 2015, 78: 203-218.
[5] VIDAL A, KRISTJANPOLLER W. Gold volatility prediction using a CNN-LSTM approach[J]. Expert Systems with Applications, 2020, 157: 113481.
[6] XIE P, LI T, LIU J, et al. Urban flow prediction from spatiotemporal data using machine learning: a survey[J]. Information Fusion, 2020, 59: 1-12.
[7] AZARBONYAD H, DEHGHANI M, MARX M, et al. Learning to rank for multi-label text classification: combining different sources of information[J]. Natural Language Engineering, 2020, 27(1): 1-23.
[8] YU Y, CAO J, ZHU J. An LSTM short-term solar irradiance forecasting under complicated weather conditions[J]. IEEE Access, 2019, 7: 145651-145666.
[9] SETHI R, KLEISSL J. Comparison of short-term load forecasting techniques[C]//2020 IEEE Conference on Technologies for Sustainability (SusTech), 2020.
[10] WU W, LIAO W, MIAO J, et al. Using gated recurrent unit network to forecast short-term load considering impact of electricity price[J]. Energy Procedia, 2019, 158: 3369-3374.
[11] TZOVARAS D. Benchmark comparison of analytical, data-based and hybrid models for multi-step short-term photovoltaic power generation forecasting[J]. Energies, 2020, 13(22): 5978.
[12] ABDEL-NASSER M. Accurate photovoltaic power forecasting models using deep LSTM-RNN[J]. Neural Computing & Applications, 2019, 31(7): 2727-2740.
[13] WU H, XU J, WANG J, et al. Autoformer: decomposition transformers with auto-correlation for long-term series forecasting[C]//Advances in Neural Information Processing Systems, 2021: 22419-22430.
[14] 智能电网调度控制系统技术规范　第2部分: 术语: GB/T 33590.2-2017[S].2017.
Techaical specification of smart grid operation and control systems. Part 2: Terminology: GB/T 33590.2-2017[S].2017.
[15] LUO X, DING H, TANG M, et al. Attention mechanism with BERT for content annotation and categorization of pregnancy-related questions on a community Q&A site[C]//2020 IEEE International Conference on Bioinformatics and Biomedicine, 2020.
[16] ZHOU H, ZHANG S, PENG J, et al. Informer: beyond efficient transformer for long sequence time-series forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2021: 11106-11115.
[17] CHO K, MERRIENBOER B V, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014.
[18] LAI G, CHANG W C, YANG Y, et al. Modeling long- and short-term temporal patterns with deep neural networks[C]//International ACM SIGIR Conference on Research and Development in Information Retrieval, 2018.
[19] KHAJEPOUR S, AMERI M. Techno-economic analysis of a hybrid solar Thermal-PV power plant[J]. Sustainable Energy Technologies and Assessments, 2020, 42: 100857.
[20] KATOH K, MISAWA K, KUMA K, et al. MAFFT: a novel method for rapid multiple sequence alignment based on fast Fourier transform[J]. Nucleic Acids Research, 2002, 30(14): 3059-3066.
[21] DKA solar centre[DB/OL]. (2020-09-28)[2022-12-29]. http://dkasolarcentre.com.