鉴于当前风电功率预测算法在堆叠建模过程所存在试错性与弱解释性问题,提出一类应用于风电功率预测的可解释性优化堆叠模型 （interpretable optimal stacking model, IOSM）。首先,建立初始冗余基学习器并进行特征权重解释;其次,构建一个综合衡量模型性能与计算代价的特征优化度量,优化关键特征并训练形成优化后的基学习器;最终,根据特征优化度量对基学习器进行优化选择,搭建得到元学习器。经如上步骤,即完成搭建IOSM。所提算法在广西典型风电场的算例表明,IOSM相对于最优单一模型的RMSE与MAE指标上分别降低13.01%和18.23%;相对于其他各类主流组合预测算法,该文算法在RMSE与MAE指标分别降低8.24%与10.28%的同时,至少降低了142.38%的建模计算代价。所提算法的有效性及先进性得到验证,为风电功率预测的可解释性优化建模上提供了新的思路与方法。
Abstract
High accuracy of wind power forecasting is an important support to ensure the balance of the power and load and stable operation of power system. In view of the trial-error and weak interpretative problems of current wind power forecasting algorithms in stack modeling, an interpretable optimal stacking model （IOSM） is proposed in this paper, which is applied to wind power forecasting. Firstly, establish an initial redundant base learner and interpret the feature weights. Further, construct a feature optimization metric that comprehensively measures model performance and computation cost, to optimize and select key features and train them to form optimized base learners. Finally, based on feature optimization metrics,the meta learner is established by the the optimized base learner. As above, the complete IOSM is constructed. The proposed algorithm is applied to typical wind farms in Guangxi. Compared with the optimal single model, the RMSE and MAE indexes of IOSM are reduced by 13.01% and 18.23% respectively. Compared with other mainstream combinatorial algorithms, the RMSE and MAE indexes of IOSM can be decreased by 8.24% and 10.28% respectively, while still reducing 142.38% modeling computation cost at least. The effectiveness and advancement of the proposed algorithm are verified, which provides a new idea and method for interpretability modeling of wind power forecasting.
关键词
风电功率预测 /
可解释性 /
堆叠模型 /
特征优化 /
集成学习
Key words
wind power forecasting /
interpretability /
stacking model /
feature optimization /
ensemble learning
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 中国可再生能源学会风能专业委员会. 2024年中国风电吊装容量统计简报[J]. 风能, 2025(3): 1-16.
CWEE. Statistical brief report on wind power hoisting capacity in China in2022[J]. Wind energy, 2023(4): 40-56.
[2] WANG N, ZHOU K P, WANG K, et al.Climate change characteristics of coastal wind energy resources in Zhejiang Province based on ERA-interim data[J]. Frontiers in physics, 2021, 9: 720533.
[3] 盛四清, 俞可, 张文朝, 等. 大规模风电并网对送端系统功角稳定的影响研究[J]. 电力系统保护与控制, 2022, 50(6): 82-90.
SHENG S Q, YU K, ZHANG W C, et al.Influence of large-scale wind power grid connection on the power angle stability of the sending end system[J]. Power system protection and control, 2022, 50(6): 82-90.
[4] 薛禹胜, 雷兴, 薛峰, 等. 关于风电不确定性对电力系统影响的评述[J]. 中国电机工程学报, 2014, 34(29): 5029-5040.
XUE Y S, LEI X, XUE F, et al.A review on impacts of wind power uncertainties on power systems[J]. Proceedings of the CSEE, 2014, 34(29): 5029-5040.
[5] 王伟胜, 王铮, 董存, 等. 中国短期风电功率预测技术现状与误差分析[J]. 电力系统自动化, 2021, 45(1): 17-27.
WANG W S, WANG Z, DONG C, et al.Status and error analysis of short-term forecasting technology of wind power in China[J]. Automation of electric power systems, 2021, 45(1): 17-27.
[6] PENG X S, LI C, JIA S Y, et al.A short-term wind power prediction method based on deep learning and multistage ensemble algorithm[J]. Wind energy, 2022, 25(9): 1610-1625.
[7] ALMUTAIRI A, ALRUMAYH O.An intelligent deep learning based prediction model for wind power generation[J]. Computers and electrical engineering, 2022, 101: 108000.
[8] ZHANG M, LI H B, DENG X.Inferential statistics and machine learning models for short-term wind power forecasting[J]. Energy engineering, 2022, 119(1): 237-252.
[9] SASSER C, YU M L, DELGADO R.Improvement of wind power prediction from meteorological characterization with machine learning models[J]. Renewable energy, 2022, 183: 491-501.
[10] 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.
[11] 凌立文, 张大斌. 组合预测模型构建方法及其应用研究综述[J]. 统计与决策, 2019, 35(1): 18-23.
LING L W, ZHANG D B.A review of construction and application of combination forecast model[J]. Statistics & decision, 2019, 35(1): 18-23.
[12] TASCIKARAOGLU A, UZUNOGLU M.A review of combined approaches for prediction of short-term wind speed and power[J]. Renewable and sustainable energy reviews, 2014, 34: 243-254.
[13] 孙荣富, 张涛, 和青, 等. 风电功率预测关键技术及应用综述[J]. 高电压技术, 2021, 47(4): 1129-1143.
SUN R F, ZHANG T, HE Q, et al.Review on key technologies and applications in wind power forecasting[J]. High voltage engineering, 2021, 47(4): 1129-1143.
[14] 李贞, 崔丽艳, 陶颍军, 等. 基于博弈论赋权的光伏功率组合预测模型[J]. 电气技术, 2017(5): 24-29.
LI Z, CUI L Y, TAO Y J, et al.The combined model for pv power forecasting based on combination weighting approach of game theory[J]. Electrical engineering, 2017(5): 24-29
[15] 陈宁, 沙倩, 汤奕, 等. 基于交叉熵理论的风电功率组合预测方法[J]. 中国电机工程学报, 2012, 32(4): 29-34, 22.
CHEN N, SHA Q, TANG Y, et al.A combination method for wind power predication based on cross entropy theory[J]. Proceedings of the CSEE, 2012, 32(4): 29-34, 22.
[16] ZHANG F, GUO Z M, SUN X H, et al.Short-term wind power prediction based on EMD-LSTM combined model[J]. IOP conference series: earth and environmental science, 2020, 514(4): 042003.
[17] 王维高, 魏云冰, 滕旭东. 基于VMD-SSA-LSSVM的短期风电预测[J]. 太阳能学报, 2023, 44(3): 204-211.
WANG W G, WEI Y B, TENG X D.Short-term wind power forecasting based on VMD-SSA-LSSVM[J]. Acta energiae solaris sinica, 2023, 44(3): 204-211.
[18] 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.
[19] 张浩田, 温蜜, 李晋国, 等. 数据驱动的时间注意力卷积风电功率预测模型[J]. 太阳能学报, 2022, 43(10): 167-176.
ZHANG H T, WEN M, LI J G, et al.Data driven time attention convolution wind power prediction model[J]. Acta energiae solaris sinica, 2022, 43(10): 167-176.
[20] WANG Y R, WANG D C, TANG Y.Clustered hybrid wind power prediction model based on ARMA, PSO-SVM, and clustering methods[J]. IEEE access, 2020, 8: 17071-17079.
[21] 刘帅, 朱永利, 张科, 等. 基于误差修正ARMA-GARCH模型的短期风电功率预测[J]. 太阳能学报, 2020, 41(10): 268-275.
LIU S, ZHU Y L, ZHANG K, et al.Short-term wind power forecasting based on error correction ARMA-GARCH model[J]. Acta energiae solaris sinica, 2020, 41(10): 268-275.
[22] CHANDRAN V, PATIL C K, MERLINE MANOHARAN A, et al.Wind power forecasting based on time series model using deep machine learning algorithms[J]. Materials today: proceedings, 2021, 47: 115-126.
[23] GANAIE M A, HU M H, MALIK A K, et al.Ensemble deep learning: a review[J]. Engineering applications of artificial intelligence, 2022, 115: 105151.
[24] DONG X B, YU Z W, CAO W M, et al.A survey on ensemble learning[J]. Frontiers of computer science, 2020, 14(2): 241-258.
[25] RIBEIRO M T, SINGH S, GUESTRIN C.“Why should I trust you?”: explaining the predictions of any classifier[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, California, USA, 2016: 1135-1144.
[26] LIANG Y, LI S G, YAN C G, et al.Explaining the black-box m odel: a survey of local interpretation methods for deep neural networks[J]. Neurocomputing, 2021, 419: 168-182.
基金
广西电网公司科技项目（046000KK52220007）
PDF(1528 KB)
