针对短期风功率预测现有预测方法缺少对序列子过程时延相似性的考虑、预测结果受制于序列分解效果以及预测精度低等问题,提出基于小波软阈值去噪（WSTD）和改进Autoformer的组合预测方法。首先,使用小波软阈值去噪对原始数据进行预处理,减少噪声对预测精度的影响;其次,将具有自相关机制的Autoformer模型应用于短期风功率预测,在序列视角下挖掘周期依赖关系;最后,基于多级离散小波变换构建深度分解架构对Autoformer模型进行改进,提高Autoformer模型对复杂时间模式的分解能力。实验结果表明,所提组合模型预测精度优于单一的模型且具有良好的适应性,在4个季节的算例中,与Autoformer模型相比RMSE和MAE指标平均下降19.86%和19.07%,R2平均提高5.15%。
Abstract
Short-term wind power prediction plays a crucial role in formulating effective power system production scheduling plans, but the inherent stochastic nature and volatility of wind power output present challenges to achieving high prediction accuracy. This paper addresses several limitations prevalent in existing prediction methods, including the neglect of time delay similarity in sequential sub-processes, reliance on sequence decomposition effects, and the suboptimal accuracy of current approaches. In response to these challenges, the WSTD-improved Autoformer combination prediction method is proposed. Firstly, the preprocessing of raw data is performed using wavelet soft threshold denoising to mitigate the impact of noise on prediction accuracy. Secondly, the Autoformer model, characterized by its autocorrelation mechanism, is employed for short-term wind power prediction, exploring periodic dependencies from a sequential perspective. Additionally, a deep decomposition architecture based on multi-level discrete wavelet transforms is constructed to enhance the Autoformer model's capability to decompose intricate temporal patterns. Experimental results demonstrate that the proposed combination prediction model outperforms individual models and exhibits excellent adaptability. In the four seasonal scenarios, the RMSE and MAE metrics decreased by an average of 19.86% and 19.07%, and the R2 increased by an average of 5.15% compared to the Autoformer model.
关键词
风功率 /
小波变换 /
自相关 /
改进Autoformer模型 /
短期预测
Key words
wind power /
wavelet transforms /
autocorrelation /
improved Autoformer model /
short-term prediction
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 杨健, 徐思卿, 姜尚光, 等. 基于动态时间规整的风电功率爬坡滚动修正模型[J]. 电力系统自动化, 2021, 45(16): 152-159.
YANG J, XU S Q, JIANG S G, et al.Rolling correction model of ramp for wind power based on dynamic time warping[J]. Automation of electric power systems, 2021, 45(16): 152-159.
[2] 丁婷婷, 杨明, 于一潇, 等. 基于误差修正的短期风电功率集成预测方法[J]. 高电压技术, 2022, 48(2): 488-496.
DING T T, YANG M, YU Y X, et al.Short-term wind power integration prediction method based on error correction[J]. High voltage engineering, 2022, 48(2): 488-496.
[3] 赵泽妮, 云斯宁, 贾凌云, 等. 基于统计模型的短期风能预测方法研究进展[J]. 太阳能学报, 2022, 43(11): 224-234.
ZHAO Z N, YUN S N, JIA L Y, et al.Recent progress in short-term forecasting of wind energy based on statistical models[J]. Acta energiae solaris sinica, 2022, 43(11): 224-234.
[4] WANG J M, ZHOU Q W, ZHANG X T.Wind power forecasting based on time series ARMA model[J]. IOP conference series: earth and environmental science, 2018, 199: 022015.
[5] 贾凌云, 云斯宁, 赵泽妮, 等. 神经网络短期光伏发电预测的应用研究进展[J]. 太阳能学报, 2022, 43(12): 88-97.
JIA L Y, YUN S N, ZHAO Z N, et al.Recent progress of short-term forecasting of photovoltaic generation based on artificial neural networks[J]. Acta energiae solaris sinica, 2022, 43(12): 88-97.
[6] 张群, 唐振浩, 王恭, 等. 基于长短时记忆网络的超短期风功率预测模型[J]. 太阳能学报, 2021, 42(10): 275-281.
ZHANG Q, TANG Z H, WANG G, et al.Ultra-short-term wind power prediction model based on long and short term memory network[J]. Acta energiae solaris sinica, 2021, 42(10): 275-281.
[7] ZHAO Z N, YUN S N, JIA L Y, et al.Hybrid VMD-CNN-GRU-based model for short-term forecasting of wind power considering spatio-temporal features[J]. Engineering applications of artificial intelligence, 2023, 121: 105982.
[8] 符杨, 任子旭, 魏书荣, 等. 基于改进LSTM-TCN模型的海上风电超短期功率预测[J]. 中国电机工程学报, 2022, 42(12): 4292-4303.
FU Y, REN Z X, WEI S R, et al.Ultra-short-term power prediction of offshore wind power based on improved LSTM-TCN model[J]. Proceedings of the CSEE, 2022, 42(12): 4292-4303.
[9] VASWANI A, SHAZEER N, PARMAR N, et al.Attention is all you need[J/OL]. https://doi.org/10.48550/arXiv.1706.03762
[10] 董俊, 刘瑞, 束洪春, 等. 基于BIRCH聚类的L-Transformer分布式光伏短期发电功率预测[J]. 高电压技术, 2024, 50(9): 3883-3893.
DONG J, LIU R, SHU H C, et al.Short-term distributed photovoltaic power generation prediction based on BIRCH clustering and L-Transformer[J]. High voltage engineering, 2024, 50(9): 3883-3893.
[11] WANG C, WANG Y, DING Z T, et al.A transformer-based method of multienergy load forecasting in integrated energy system[J]. IEEE transactions on smart grid, 2022, 13(4): 2703-2714.
[12] WANG Z Y, ZHU Z, XIAO G Y, et al.A transformer-based multi-entity load forecasting method for integrated energy systems[J]. Frontiers in energy research, 2022, 10: 952420.
[13] PAN X X, WANG L, WANG Z J, et al.Short-term wind speed forecasting based on spatial-temporal graph transformer networks[J]. Energy, 2022, 253: 124095.
[14] WU B R, WANG L, ZENG Y R.Interpretable wind speed prediction with multivariate time series and temporal fusion transformers[J]. Energy, 2022, 252: 123990.
[15] WU H, XU J, WANG J, et al.Autoformer: decomposition Transformers with auto-correlation for long-term series forecasting[J]. Advances in neural information processing systems, 2021, 34: 22419-22430.
[16] JIANG Y Q, GAO T L, DAI Y X, et al.Very short-term residential load forecasting based on deep-autoformer[J]. Applied energy, 2022, 328: 120120.
[17] WANG Z Q, CHEN Z H, YANG Y, et al.A hybrid Autoformer framework for electricity demand forecasting[J]. Energy reports, 2023, 9: 3800-3812.
[18] 范杏蕊, 李元诚. 基于改进Autoformer模型的短期电力负荷预测[J]. 电力自动化设备, 2024, 44(4): 171-177.
FAN X R, LI Y C.Short-term power load forecasting based on improved Autoformer model[J]. Electric power automation equipment, 2024, 44(4): 171-177.
[19] 窦嘉炜, 杨小煜, 杨晓忠. 基于分数阶小波变换的电力系统谐波检测方法[J]. 中国电机工程学报, 2024, 44(3): 872-880.
DOU J W, YANG X Y, YANG X Z.A power system harmonic detection method based on fractional wavelet transform[J]. Proceedings of the CSEE, 2024, 44(3): 872-880.
[20] PENG S B, CHEN R L, YU B, et al.Daily natural gas load forecasting based on the combination of long short term memory, local mean decomposition, and wavelet threshold denoising algorithm[J]. Journal of natural gas science and engineering, 2021, 95: 104175.
[21] BENTSEN L Ø, WARAKAGODA N D, STENBRO R, et al.Spatio-temporal wind speed forecasting using graph networks and novel Transformer architectures[J]. Applied energy, 2023, 333: 120565.
[22] LI J, LI Y, LI Y, et al.Downhole microseismic signal denoising via empirical wavelet transform and adaptive thresholding[J]. Journal of geophysics and engineering, 2018, 15(6): 2469-2480.
[23] JERONYMO D C, BORGES Y C C, DOS SANTOS COELHO L. Image forgery detection by semi-automatic wavelet soft-Thresholding with error level analysis[J]. Expert systems with applications, 2017, 85: 348-356.
[24] 石立贤, 金怀平, 杨彪, 等. 基于局部学习和多目标优化的选择性异质集成超短期风电功率预测方法[J]. 电网技术, 2022, 46(2): 568-577.
SHI L X, JIN H P, YANG B, et al.Selective heterogeneous ensemble for ultra-short-term wind power forecasting based on local learning and multi-objective optimization[J]. Power system technology, 2022, 46(2): 568-577.
[25] 孟安波, 陈顺, 王陈恩, 等. 基于混沌CSO优化时序注意力GRU模型的超短期风电功率预测[J]. 电网技术, 2021, 45(12): 4692-4700.
MENG A B, CHEN S, WANG C E, et al.Ultra-short-term wind power prediction based on chaotic CSO optimized temporal attention GRU model[J]. Power system technology, 2021, 45(12): 4692-4700.
PDF(1953 KB)
