Abstract
Accurate ultrashort-term forecasting of mid–low-altitude wind is essential to the safe and stable flight of aircraft. Traditional artificial intelligence (AI) wind forecasting methods convert the dynamic time series regression problem into a static spatial modeling problem, while ignoring the dynamic characteristics of the wind as a typical time series, and the prediction accuracy is limited. In this paper, the long short-term memory (LSTM) network is used to dynamically model the time series of wind speed to realize ultrashort-term forecasting at mid–low altitudes. The measured data of wind lidar are used to verify the conclusions. The results show that the performance of LSTM model outperforms artificial neural network and support vector machine.
Foundation items: National Natural Science Foundation of China (61505036), the Fund Project of Guizhou Provincial Science and Technology Department (QKHJZ [2015] 2009).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
QU Yanlu. Ballistae Meteorology [M]. Beijing: China Meteorology Press, 1987, 162–165.
Lei Xusheng, Tao Ye. Adaptive Control for Small Unmanned Aerial Vehicle Under Wind Disturbance [J]. Acta Aeronautica Et Astronautica Sinica, 2010, 31(6): 1171–1176.
He YL, Chen YM, Zhou M. Modeling and control of a quadrotor helicopter under impact of wind disturbance[J]. Journal of Chinese Inertial Technology, 2013, 21(5): 624–630.
Costa A, Crespo A, Navarro J, et al. A review on the young history of the wind power short-term prediction [J]. Renewable and Sustainable Energy Reviews, 2008, 12(6): 1725–1744.
Yang Xiuyuan, Xiao Yang, Chen Shuyong. Wind speed and generated power forecasting in wind farm[J]. Proceedings of the CSEE, 2005, 25(11): 1–5.
Hochreiter S, Schmidhuber J. Long short-term memory [J]. Neural computation, 1997, 9(8): 1735–1780.
Graves A, Wayne G, Danihelka I. Neural turing machines [J]. arXiv preprint arXiv:1410.5401, 2014.
Zhang Peng, Yang Tao, Liu Yananet al. Feature extraction and prediction of QAR data based on CNN-LSTM [J/OL]. Application Research of Computers, 2019(10):1–7.
Bengio Y, Simard P, Frasconi P. Learning long-term dependencies with gradient descent is difficult [J].IEEE Transactions on Neural Networks, 1994, 5(2):157–166.
Chang F, Chang C, Huang H, et al. Real-time recurrent learning network for stream-flow forecasting [J]. Hydrological Processes 2002,16(13):2577–2588.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, C. et al. (2019). Ultrashort-Term Forecasting of Mid–Low-Altitude Wind Based on LSTM. In: Wang, L., Wu, Y., Gong, J. (eds) Proceedings of the 5th China High Resolution Earth Observation Conference (CHREOC 2018). CHREOC 2018. Lecture Notes in Electrical Engineering, vol 552. Springer, Singapore. https://doi.org/10.1007/978-981-13-6553-9_12
Download citation
DOI: https://doi.org/10.1007/978-981-13-6553-9_12
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-6552-2
Online ISBN: 978-981-13-6553-9
eBook Packages: EngineeringEngineering (R0)