Power Forecasting of Regional Wind Farms via Variational Auto-Encoder and Deep Hybrid Transfer Learning

被引:17
作者
Khan, Mansoor [1 ]
Naeem, Muhammad Rashid [2 ]
Al-Ammar, Essam A. [3 ,4 ]
Ko, Wonsuk [3 ]
Vettikalladi, Hamsakutty [3 ]
Ahmad, Irfan [3 ]
机构
[1] Leshan Normal Univ, Sch Elect & Mat Engn, Leshan 614000, Peoples R China
[2] Leshan Normal Univ, Sch Artificial Intelligence, Leshan 614000, Peoples R China
[3] King Saud Univ, Coll Engn, Dept Elect Engn, Riyadh 11421, Saudi Arabia
[4] KA CARE Energy Res & Innovat Ctr, Riyadh 12244, Saudi Arabia
关键词
wind power forecasting; variational auto-encoder; transfer learning; hybrid method; deep neural network; windfarm; ABSOLUTE ERROR MAE; NEURAL-NETWORK; SPEED; ENERGY; RMSE;
D O I
10.3390/electronics11020206
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Wind power is a sustainable green energy source. Power forecasting via deep learning is essential due to diverse wind behavior and uncertainty in geological and climatic conditions. However, the volatile, nonlinear and intermittent behavior of wind makes it difficult to design reliable forecasting models. This paper introduces a new approach using variational auto-encoding and hybrid transfer learning to forecast wind power for large-scale regional windfarms. Transfer learning is applied to windfarm data collections to boost model training. However, multiregional windfarms consist of different wind and weather conditions, which makes it difficult to apply transfer learning. Therefore, we propose a hybrid transfer learning method consisting of two feature spaces; the first was obtained from an already trained model, while the second, small feature set was obtained from a current windfarm for retraining. Finally, the hybrid transferred neural networks were fine-tuned for different windfarms to achieve precise power forecasting. A comparison with other state-of-the-art approaches revealed that the proposed method outperforms previous techniques, achieving a lower mean absolute error (MAE), i.e., between 0.010 to 0.044, and a lowest root mean square error (RMSE), i.e., between 0.085 to 0.159. The normalized MAE and RMSE was 0.020, and the accuracy losses were less than 5%. The overall performance showed that the proposed hybrid model offers maximum wind power forecasting accuracy with minimal error.
引用
收藏
页数:20
相关论文
共 54 条
[1]  
Abadi M, 2016, ACM SIGPLAN NOTICES, V51, P1, DOI [10.1145/2951913.2976746, 10.1145/3022670.2976746]
[2]  
Alhagry S, 2017, INT J ADV COMPUT SC, V8, P355, DOI 10.14569/IJACSA.2017.081046
[3]   TFX: A TensorFlow-Based Production-Scale Machine Learning Platform [J].
Baylor, Denis ;
Breck, Eric ;
Cheng, Heng-Tze ;
Fiedel, Noah ;
Foo, Chuan Yu ;
Haque, Zakaria ;
Haykal, Salem ;
Ispir, Mustafa ;
Jain, Vihan ;
Koc, Levent ;
Koo, Chiu Yuen ;
Lew, Lukasz ;
Mewald, Clemens ;
Modi, Akshay Naresh ;
Polyzotis, Neoklis ;
Ramesh, Sukriti ;
Roy, Sudip ;
Whang, Steven Euijong ;
Wicke, Martin ;
Wilkiewicz, Jarek ;
Zhang, Xin ;
Zinkevich, Martin .
KDD'17: PROCEEDINGS OF THE 23RD ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2017, :1387-1395
[4]   Wind Turbine Power Output Prediction Model Design Based on Artificial Neural Networks and Climatic Spatiotemporal Data [J].
Bilal, B. ;
Ndongo, M. ;
Adjallah, K. H. ;
Sava, A. ;
Kebe, C. M. F. ;
Ndiaye, P. A. ;
Sambou, V .
2018 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY (ICIT), 2018, :1085-1092
[5]   Temporally explicit and spatially resolved global offshore wind energy potentials [J].
Bosch, Jonathan ;
Staffell, Iain ;
Hawkes, Adam D. .
ENERGY, 2018, 163 :766-781
[6]   Root mean square error (RMSE) or mean absolute error (MAE)? - Arguments against avoiding RMSE in the literature [J].
Chai, T. ;
Draxler, R. R. .
GEOSCIENTIFIC MODEL DEVELOPMENT, 2014, 7 (03) :1247-1250
[7]   An improved neural network-based approach for short-term wind speed and power forecast [J].
Chang, G. W. ;
Lu, H. J. ;
Chang, Y. R. ;
Lee, Y. D. .
RENEWABLE ENERGY, 2017, 105 :301-311
[8]  
Chang W.-Y., 2014, Journal of Power and Energy Engineering, V02, P161
[9]   Electricity demand forecasting over Italy: Potential benefits using numerical weather prediction models [J].
De Felice, Matteo ;
Alessandri, Andrea ;
Ruti, Paolo M. .
ELECTRIC POWER SYSTEMS RESEARCH, 2013, 104 :71-79
[10]   Europe, China and the United States: Three different approaches to the development of offshore wind energy [J].
Decastro, M. ;
Salvador, S. ;
Gomez-Gesteira, M. ;
Costoya, X. ;
Carvalho, D. ;
Sanz-Larruga, F. J. ;
Gimeno, L. .
RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2019, 109 :55-70