NEW ENERGY POWER FORECASTING BASED ON ENSEMBLE LEARNING

Chen Yunpeng; Jing Chao; Bai Jingbo; Ma Jianghai; Ma Fei

doi:10.19912/j.0254-0096.tynxb.2023-0200

PDF(1928 KB)

Acta Energiae Solaris Sinica ›› 2024, Vol. 45 ›› Issue (6) : 412-421. DOI: 10.19912/j.0254-0096.tynxb.2023-0200

NEW ENERGY POWER FORECASTING BASED ON ENSEMBLE LEARNING

Chen Yunpeng¹, Jing Chao², Bai Jingbo¹, Ma Jianghai¹, Ma Fei¹

Author information +

History +

Abstract

Considering the fact that most of the existing new energy power prediction methods have difficulty in deeply mining the characteristics of time series data of multi-dimensional variables and result in poor prediction accuracy, a new energy power prediction method based on ensemble learning is proposed. Firstly, three correlation coefficients are combined with the Shapley value method to obtain variables with high correlation. Secondly, the dilated causal-convolutional neural network is used to capture the characteristics of historical power time series data, and the bidirectional-gated recurrent unit network is used to extract the variable features from the past and future combined with the temporal pattern attention. Finally, the outputs of different networks are fused according to the Stacking method. Experiments show that the proposed method achieves impressive prediction accuracy in the ultra-short term and the prediction results outperform the other comparison models.

Key words

new energy / forecasting / ensemble learning / neural network / attention mechanism

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Chen Yunpeng, Jing Chao, Bai Jingbo, Ma Jianghai, Ma Fei. NEW ENERGY POWER FORECASTING BASED ON ENSEMBLE LEARNING[J]. Acta Energiae Solaris Sinica. 2024, 45(6): 412-421 https://doi.org/10.19912/j.0254-0096.tynxb.2023-0200

References

[1] 黄强, 郭怿, 江建华, 等. “双碳” 目标下中国清洁电力发展路径[J]. 上海交通大学学报, 2021, 55(12): 1499-1509.
HUANG Q, GUO Y, JIANG J H, et al.Development pathway of China's clean electricity under carbon peaking and carbon neutrality goals[J]. Journal of Shanghai Jiao Tong University, 2021, 55(12): 1499-1509.
[2] 徐林, 黄晓莉, 杜忠明, 等. 适应新能源发展的电力规划方法研究[J]. 中国电力, 2017, 50(9): 18-24.
XU L, HUANG X L, DU Z M, et al.Study on power system planning method adapting to new energy development[J]. Electric power, 2017, 50(9): 18-24.
[3] 牛东晓, 纪会争. 风电功率物理预测模型引入误差量化分析方法[J]. 电力系统自动化, 2020, 44(8): 57-65.
NIU D X, JI H Z.Quantitative analysis method for errors introduced by physical prediction model of wind power[J]. Automation of electric power systems, 2020, 44(8): 57-65.
[4] 梁琛, 王鹏, 韩肖清, 等. 基于间歇性风速的风力发电机功率输出模型研究[J]. 电网技术, 2017, 41(5): 1369-1375.
LIANG C, WANG P, HAN X Q, et al.Intermittent wind speed model and wind turbine output model[J]. Power system technology, 2017, 41(5): 1369-1375.
[5] 乔颖, 鲁宗相, 闵勇. 提高风电功率预测精度的方法[J]. 电网技术, 2017, 41(10): 3261-3269.
QIAO Y, LU Z X, MIN Y.Research & application of raising wind power prediction accuracy[J]. Power system technology, 2017, 41(10): 3261-3269.
[6] 朱乔木, 李弘毅, 王子琪, 等. 基于长短期记忆网络的风电场发电功率超短期预测[J]. 电网技术, 2017, 41(12): 3797-3802.
ZHU Q M, LI H Y, WANG Z Q, et al.Short-term wind power forecasting based on LSTM[J]. Power system technology, 2017, 41(12): 3797-3802.
[7] OOKURA S, MORI H.An efficient method for wind power generation forecasting by LSTM in consideration of overfitting prevention[J]. IFAC-PapersOnLine, 2020, 53(2): 12169-12174.
[8] 李锦程. 基于门控循环单元的短期风电功率预测研究[D]. 徐州: 中国矿业大学, 2019.
LI J C.Research on short-term wind power forecasting based on gated recurrent unit[D]. Xuzhou: China University of Mining and Technology, 2019.
[9] WU Q Y, GUAN F, LYU C, et al.Ultra-short-term multi-step wind power forecasting based on CNN-LSTM[J]. IET renewable power generation, 2021, 15(5): 1019-1029.
[10] 贾睿, 杨国华, 郑豪丰, 等. 基于自适应权重的CNN-LSTM&GRU组合风电功率预测方法[J]. 中国电力, 2022, 55(5): 47-56, 110.
JIA R, YANG G H, ZHENG H F, et al.Combined wind power prediction method based on CNN-LSTM & GRU with adaptive weights[J]. Electric power, 2022, 55(5): 47-56, 110.
[11] 景惠甜. 基于深度学习的风电功率预测研究[D]. 徐州: 中国矿业大学, 2021.
JING H T.Research on wind power forecasting based on deep learning[D]. Xuzhou: China University of Mining and Technology, 2021.
[12] BAI S J, KOLTER J Z, KOLTUN V, et al. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[EB/OL].2018: 1803.01271.http://arxiv.org/abs/1803.01271v2.
[13] 韩朋, 张晓琳, 张飞, 等. 基于AM-LSTM模型的超短期风电功率预测[J]. 科学技术与工程, 2020, 20(21): 8594-8600.
HAN P, ZHANG X L, ZHANG F, et al.Ultra-short-term wind power prediction based on AM-LSTM model[J]. Science technology and engineering, 2020, 20(21): 8594-8600.
[14] 姚越, 刘达. 基于注意力机制的卷积神经网络-长短期记忆网络的短期风电功率预测[J]. 现代电力, 2022, 39(2): 212-218.
YAO Y, LIU D.Short-term wind power forecasting based on attention mechanism of CNN-LSTM[J]. Modern electric power, 2022, 39(2): 212-218.
[15] 康文豪, 徐天奇, 王阳光, 等. 基于CEEMDAN-精细复合多尺度熵和Stacking集成学习的短期风电功率预测[J]. 水利水电技术(中英文), 2022, 53(2): 163-172.
KANG W H, XU T Q, WANG Y G, et al.CEEMDAN-refined composite multiscale entropy and stacking ensemble learning-based short-term wind power prediction[J]. Water resources and hydropower engineering, 2022, 53(2): 163-172.
[16] 鲁泓壮, 丁云飞, 汪鹏宇. 基于信息融合和堆叠模型的超短期风电功率预测[J]. 可再生能源, 2022, 40(3): 344-349.
LU H Z, DING Y F, WANG P Y.Ultra-short-term wind power forecasting based on information fusion and stacking model[J]. Renewable energy resources, 2022, 40(3): 344-349.
[17] 赵龙. 基于NWP和改进BP神经网络的风电功率预测研究[D]. 北京: 北京交通大学, 2015.
ZHAO L.Research on wind power prediction based on NWP and the improved BP neural network[D]. Beijing: Beijing Jiaotong University, 2015.
[18] 刘仍祥. 相关性指标及其置信区间在季风风速预测中的应用[D]. 天津: 天津大学, 2018.
LIU R X.Application of similarity index and its confidence intervals in prediction of monsoon wind speed[D]. Tianjin: Tianjin University, 2018.
[19] 康文豪, 徐天奇, 王阳光, 等. 基于特征选择和改进深度森林的短期风电功率预测[J]. 陕西科技大学学报, 2021, 39(6): 148-153, 188.
KANG W H, XU T Q, WANG Y G, et al.Short-term wind power prediction based on feature selection and improved deep forest[J]. Journal of Shaanxi University of Science & Technology, 2021, 39(6): 148-153, 188.
[20] ZHANG J A, LIU D, LI Z J, et al.Power prediction of a wind farm cluster based on spatiotemporal correlations[J]. Applied energy, 2021, 302: 117568.
[21] 贾茹. 基于集成学习的风电功率预测方法研究[D]. 沈阳: 东北大学, 2019.
JIA R.Research on wind power forecasting approach based on ensemble learning[D]. Shenyang: Northeastern University, 2019.
[22] SHIVAM K, TZOU J C, WU S C.Multi-step short-term wind speed prediction using a residual dilated causal convolutional network with nonlinear attention[J]. Energies, 2020, 13(7): 1772.
[23] YILDIZ C, ACIKGOZ H, KORKMAZ D, et al.An improved residual-based convolutional neural network for very short-term wind power forecasting[J]. Energy conversion and management, 2021, 228: 113731.
[24] ZHENG Z J, FENG L, WANG X, et al.Multi-energy load forecasting model based on bi-directional gated recurrent unit multi-task neural network[J]. E3S web of conferences, 2021, 256: 02032.
[25] SHIH S Y, SUN F K, LEE H Y.Temporal pattern attention for multivariate time series forecasting[J]. Machine learning, 2019, 108(8): 1421-1441.
[26] TANG B, CHEN Y, CHEN Q, et al.Research on short-term wind power forecasting by data mining on historical wind resource[J]. Applied sciences, 2020, 10(4): 1295.
[27] 刘倩. 风电场功率预测数据清洗方法研究及应用[D]. 北京: 华北电力大学, 2020.
LIU Q.Research and application of wind farm power forecast data cleaning method[D]. Beijing: North China Electric Power University, 2020.
[28] AN G Q, JIANG Z Y, CHEN L B, et al.Ultra short-term wind power forecasting based on sparrow search algorithm optimization deep extreme learning machine[J]. Sustainability, 2021, 13(18): 10453.
[29] 李大中, 李颖宇. 基于深度学习与误差修正的超短期风电功率预测[J]. 太阳能学报, 2021, 42(12): 200-205.
LI D Z, LI Y Y.Ultra-short term wind power prediction based on deep learning and error correction[J]. Acta energiae solaris sinica, 2021, 42(12): 200-205.