Short-term Prediction Method of Wind Field Using Improved ConvLSTM Model
Pages 58 - 64
Abstract
Disaster weather greatly affects the quality and yield of fruit trees. Improving the ability of wind speed simulation and prediction enable fruit farmers to prepare for meteorological disasters in advance and reduce the losses of fruit farmers. Aiming at the inductive preference of traditional neural networks, this paper proposes an improved convolutional long short-term memory (ConvLSTM) method for short-term prediction of wind field. For the data of wind speed produced by the meteorological stations, the grid data obtained by thin plate spline (TPS) interpolation is fused with National Centers for Environmental Prediction (NCEP) wind speed data to improve the accuracy; the regularization loss function is introduced to improve the ConvLSTM model and improve the short-term prediction capacity of mountain wind fields under complex terrain. The experimental results show that the proposed method can obtain higher short-term prediction accuracy of wind field.
References
[1]
News 2014. Kunming information port. Retrieved August 10, 2020 from https://www.kunming.cn/news/c/2014-07-24/3639550.shtml.
[2]
Qiu Si.1995. Wind hazards to fruit trees and preventive measures. Forestry in Inner Mongolia, 01,26.
[3]
Qinqin Chen, Guo Chu.2014. Short-term wind speed prediction model for wind farms based on statistical clustering and times series analysis. Journal of Shanghai Dianji University,17(2):77-82.
[4]
Hang Fan, Xuemei Zhang, Shengwei Mei. 2021. Ultra-short-term wind speed prediction model for wind farms based on spatio-temporal neural network. Automation of Power Systems, 45(1):28-34.
[5]
Yuxin Meng, Ruihan Wang, Xiping Zhang,et al. 2021. Ultra-short-term wind power prediction based on empirical modal decomposition and multi-branch neural networks. Journal of Computer Applications, 41(1):237-242.
[6]
Yuqi Li, Ganglin Zhang, Min Gan. 2017. Wind speed time series prediction based on autoregressive model of the functional system. Mathmatics in Practice and Theory, 47(8):161-166.
[7]
Hodge Bri-Mathias, Zeiler Austin, Brooks Duncan,et al. Improved wind power forecasting with ARIMA models. Computer Aided Chemical Engineering, 29:1789-1793.
[8]
Qiaomu Zhu, Hongyi Li, Ziqi Wang,et al. 2017. Ultra-short-term forecast of wind farm power generation power based on long-term short-term memory network. Journal of Power Grid Technology, 41(12):3797-3802.
[9]
Yang Xue, Lin Wang, Shu Wang,et al. 2019. An ultra-short-term wind power forecasting model that combines CNN and GRU networks. Renewable Energy Journal, 37(3):456-462.
[10]
Sepp Hochreiter, and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Computation, 9(8): 1735-1780.
[11]
Xingjian Shi, Zhourong Chen, Hao Wang,et al. 2015. Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. Advances in Neural Information Processing Systems, 802-810.
[12]
Tibshirani R. 1996. Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society. Series B: Statistical Methodology, 58(1):267-288.
[13]
Yan Shen, Ping Zhao, Yang Pan,et al. 2014. A high spatiotemporal gauge-satellite merged precipitation analysis over China. Journal of Geophysical Research: Atmospheres,119(6):3063-3075.
[14]
Ushio T, Sasashige K, Kubota T,et al. 2009. A Kalman filter approach to the Global Satellite Mapping of Precipitation(GSMap) from combined passive microwave and infrared radiometric data. Journal of the Meteorological Society of Japan, 87:137-151.
[15]
Hill D J. 2015. Assimilation of weather radar and binary ubiquitous sensor measurements for quantitative precipitation estimation. Journal of Hydroinformatics, 17(4):598-613.
[16]
Pingping Xie, Anyuan Xiong. 2011. A conceptual model for constructing high-resolution gauge-satellite merged precipitation analyses. Journal of Geophysical Research Atmospheres,116(21):148-227.
[17]
Pradhan B, Jebur M N, Shafri H Z M,et al. 2016. Data fusion technique using wavelet transform and Taguchi methods for automatic landslide detection from airborne laser scanning data and quickbird satellite imagery. IEEE Transactions on Geoscience and Remote Sensing, 1610-1622.
[18]
Huan Li, Yang Hong, Pingping Xie. 2015. Variational merged of hourly gauge-satellite precipitation in China: Preliminary results. Journal of Geophysical Research,120(19):9897-9915.
[19]
Jinjun Ren, Ning Wang. 2018. Study of the loss function in artificial neural networks. Journal of Gansu Higher Teachers,23(2):61-63.
[20]
Donald Shepard. 1968. A Two-dimensional Interpolation Function for Irregularly-Spaced Data. In Proceedings of the 1968 ACM National Conference, New York, NY, USA, 517-524.
[21]
Wanba Grace. 1979. How to smooth curves and surfaces with splines and cross validation. In Proceedings of the 24th Design of Experiments Conference, US Army Research Office,167-192.
[22]
Wanba Grace.1990. Splines models for observational data. Philadelphia: Society for Industrial and Applied Mathematics.
Index Terms
- Short-term Prediction Method of Wind Field Using Improved ConvLSTM Model
Recommendations
Short Term Wind Speed Forecasting for Wind Farms Using an Improved Autoregression Method
ICM '11: Proceedings of the 2011 International Conference of Information Technology, Computer Engineering and Management Sciences - Volume 01A new method in wind speed prediction based on auto regression (AR) method is proposed. The new method not only takes actual range of predicted value into account but also combines AR with the mean filter of the wind speed waveform. The restriction on ...
An ultra-short-term wind speed prediction model using LSTM and CNN
AbstractGale weather can easily cause high-speed train accidents such as derailment and rollover. Therefore, the ultra-short-term prediction of wind speed is of great significance for a safe operation of high-speed rail. A prediction model based on long ...
Short-term wind speed combination prediction model based on multiple models
CIBDA '24: Proceedings of the 5th International Conference on Computer Information and Big Data ApplicationsA model for predicting short-term wind speed is proposed with the aim of addressing the issue of low accuracy in short-term wind speed. In order to decrease the data dimension, the nuclear principal component analysis is used to identify the principle ...
Comments
Information & Contributors
Information
Published In
September 2022
215 pages
ISBN:9781450397551
DOI:10.1145/3568199
Copyright © 2022 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 06 March 2023
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Funding Sources
- Major Science and Technology Special Plan Project in Yunnan Province
Conference
MLMI 2022
MLMI 2022: 2022 5th International Conference on Machine Learning and Machine Intelligence
September 23 - 25, 2022
Hangzhou, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 32Total Downloads
- Downloads (Last 12 months)19
- Downloads (Last 6 weeks)2
Reflects downloads up to 18 Aug 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format