An innovative interpretable combined learning model for wind speed forecasting

被引:26
作者
Du, Pei [1 ]
Yang, Dongchuan [2 ]
Li, Yanzhao [2 ]
Wang, Jianzhou [3 ]
机构
[1] Jiangnan Univ, Sch business, Wuxi 214122, Peoples R China
[2] Xi An Jiao Tong Univ, Sch Management, Xian 710049, Peoples R China
[3] Macau Univ Sci & Technol, Inst Syst Engn, Taipa 999078, Macao, Peoples R China
关键词
Combined forecasting; Interpretable forecasting; Wind speed forecasting; Deep learning; NEURAL-NETWORKS; ENSEMBLE; PREDICTION; REGRESSION; OPTIMIZATION; COMBINATION; MULTISTEP; ALGORITHM; MACHINE; SYSTEM;
D O I
10.1016/j.apenergy.2023.122553
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Wind energy is taken as one of the most potential green energy sources, whose accurate and stable prediction is important to improve the efficiency of wind turbines as well as to guarantee the power balance and economic dispatch of power systems and equipment safety. However, the random and fluctuating nature of wind speed poses a great risk to wind power grid connections. To address the issues of low prediction performance and lack of interpretable analysis in most past studies, this research proposes an interpretable combined learning model for wind speed time series prediction by combining linear models, different neural networks, and deep learning by introducing interpretable TFT models. To test the effectiveness of the forecasting models, the presented combined model is verified using eight wind speed datasets covering four seasons collected from two wind farms in Shaanxi, China. The experimental results show that the average root mean squared error of the one-step, twostep, and three -step predictions on the eight datasets for proposed model are 0.3448, 0.4586 and 0.6164, respectively, which are much better than the six single models and the six combined models with different strategies. And proposed model outperforms the single model and combined model in most cases, with 86.80% and 92.01% of the DM values greater than the corresponding critical values when the significance level is set to 0.01 and 0.1, respectively. Finally, the proposed model is discussed and analyzed in depth through interpretability analysis of the combined model, which further validates the potential of the model and also provides a reference for other time series forecasting studies.
引用
收藏
页数:20
相关论文
共 72 条
[1]   NEW LOOK AT STATISTICAL-MODEL IDENTIFICATION [J].
AKAIKE, H .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1974, AC19 (06) :716-723
[2]  
[Anonymous], 2009, Deep belief networks4
[3]  
[Anonymous], 2016, International Journal of Control Theory and Applications
[4]   COMBINATION OF FORECASTS [J].
BATES, JM ;
GRANGER, CWJ .
OPERATIONAL RESEARCH QUARTERLY, 1969, 20 (04) :451-&
[5]  
Box GEP G.M., 1976, Jenkins time series analysis: Forecasting and control
[6]   Dynamic ensemble wind speed prediction model based on hybrid deep reinforcement learning [J].
Chen, Chao ;
Liu, Hui .
ADVANCED ENGINEERING INFORMATICS, 2021, 48
[7]   Wind speed forecasting using nonlinear-learning ensemble of deep learning time series prediction and extremal optimization [J].
Chen, Jie ;
Zeng, Guo-Qiang ;
Zhou, Wuneng ;
Du, Wei ;
Lu, Kang-Di .
ENERGY CONVERSION AND MANAGEMENT, 2018, 165 :681-695
[8]   A Two-Layer Nonlinear Combination Method for Short-Term Wind Speed Prediction Based on ELM, ENN, and LSTM [J].
Chen, Min-Rong ;
Zeng, Guo-Qiang ;
Lu, Kang-Di ;
Weng, Jian .
IEEE INTERNET OF THINGS JOURNAL, 2019, 6 (04) :6997-7010
[9]   LPG-model: A novel model for throughput prediction in stream processing, using a light gradient boosting machine, incremental principal component analysis, and deep gated recurrent unit network [J].
Chu, Zheng ;
Yu, Jiong ;
Hamdulla, Askar .
INFORMATION SCIENCES, 2020, 535 :107-129
[10]   Automatic detection method of cracks from concrete surface imagery using two-step light gradient boosting machine [J].
Chun, Pang-jo ;
Izumi, Shota ;
Yamane, Tatsuro .
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, 2021, 36 (01) :61-72