基于FOA-FSVM的RF模式台风期阵风精细化预报
PDF下载 (375)何彩芬1,钱斌凯2,金 炜2*,张国超1.基于FOA-FSVM的RF模式台风期阵风精细化预报[J].宁波大学学报(理工版),2018,31(6):20-26.DOI:
HE Cai-fen1,QIAN Bin-kai2,JIN Wei2*,ZHANG Guo-chao1.Precision forecasting of typhoon wind speed in WRF model based on IFOA-FSVM[J].Journal of Ningbo University(Natural Science & Engineering Edition),2018,31(6):20-26.DOI:
| Title: | Precision forecasting of typhoon wind speed in WRF model based on IFOA-FSVM |
| 作者: | 何彩芬1, 钱斌凯2, 金 炜2*, 张国超1 |
| Author(s): | HE Cai-fen1, QIAN Bin-kai2, JIN Wei2*, ZHANG Guo-chao1 |
| 关键词: | 果蝇优化算法; 模糊支持向量机; 风速预测; 台风 |
| Keywords: | fruit fly optimization algorithm; fuzzy support vector machine; wind speed forecasting; typhoon |
| 分类号: | TP391 |
| 文献标识码: | A |
| 摘要: | 为提高天气预报模式 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">(Weather Research and Forecasting Model, WRF) 输出中台风期阵风的预测精度 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">, 将 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">WRF 模式输出与某观测站实况数据相结合 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">, 提出一种台风期阵风精细化预报方法 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">. 针对影响台风风速的因素众多 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">, 而传统依据人工经验预判的风速存在较大误差的现状 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">, 该方法构建了台风期阵风预测的模糊支持向量回归模型 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">, 同时为解决模糊支持向量回归模型中惩罚因子 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">C 和核参数 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">g 难于确定的问题 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">, 将果蝇优化算法 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">(Fruit Fly Optimization Algorithm, FOA) 引入到模糊支持向量机 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">(Fuzzy Support Vector Machine, FSVM) 的参数寻优中 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">, 并根据风速回归的特点 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">, 把果蝇优化算法引入到三维空间 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">, 结合增强因子 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">γ 以提高传统果蝇优化算法的全局寻优能力 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">. 实验结果表明 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">, 本文构建的模型预测风速与实际风速基本一致 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">, 相关性达到 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">99 ％ <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">, 不仅提高了 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">WRF 模式风速的适用性 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">, 而且风速预测精度明显优于传统 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">FOA-FSVM 和 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">FOA-SVM 方法 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">, 具有更强的泛化能力 <span style="FONT-SIZE: 10.5pt; FONT-FAMILY: "Times New Roman"">. |
| Abstract: | For the sake of improving the accuracy of forecasting wind speed during typhoon strike in WRF model forecast, a new method for precision forecasting of typhoon wind speed is proposed by combining the data collected from the WRF model forecast and an automatic observation station. The method incorporates many factors influencing the typhoon wind speed. The wind speed which is obtained using the traditional human prediction produces large error when compared with actual wind speed. To address this issue, a fuzzy support vector regression model for wind forecasting is built. Considering the fact that the fuzzy support vector regression model is not adequately efficient in determining the punishment factor and kernel parameter, the fly optimization algorithm is introduced into optimizing the parameters of the fuzzy support vector machine. According to the characteristics of the wind speed regression, the fruit fly optimization algorithm is developed in three dimensional space, combining with the enhancement factor γ for improving the global optimization ability of traditional fruit fly optimization algorithm. The results show that the forecasting wind speed and the actual one is in good agreement with each other, and the correlation is as high as 99％. The presented method of wind speed prediction provides higher accuracy than that of traditional FOA-FSVM model and FOA-SVM model. |
| 参考文献 /References: | [1] Kerem A, Kirbas I, Saygin A. Performance analysis of time series forecasting models for short term wind speed prediction[EB/OL]. [2018-01-10]. https://www.researchgate. net/publication/312891204_Performance_Analysis_of_Time_Series_Forecasting_Models_for_Short_Term_Wind_Speed_Prediction. [2] Gauterin E, Kammerer P, Kühn M, et al. Effective wind speed estimation: Comparison between Kalman filter and Takagi-Sugeno observer techniques[J]. Isa Transactions, 2016, 62:60-72. [3] Galanis G, Papageorgiou E, Liakatas A. A hybrid Bayesian Kalman filter and applications to numerical wind speed modeling[J]. Journal of Wind Engineering & Industrial Aerodynamics, 2017, 167:1-22. [4] Finamore A R, Galdi V, Calderaro V, et al. Artificial neural network application in wind forecasting: A one- hour-ahead wind speed prediction[EB/OL]. [2018-01-10]. https://ieeexplore.ieee.org/document/7835492. [5] 解坤, 张俊芳. 基于KMO-Bartlett典型风速选取的PCA-WNN短期风速预测[J]. 发电设备, 2017, 31(2): 86-91. [6] Shao H, Wei H, Deng X, et al. Short-term wind speed forecasting using wavelet transformation and AdaBoosting neural networks in Yunnan wind farm[J]. IET Renewable Power Generation, 2017, 11(4):374-381. [7] 颜晓娟, 龚仁喜, 张千锋. 优化遗传算法寻优的SVM在短期风速预测中的应用[J]. 电力系统保护与控制, 2016, 44(9):38-42. [8] Cristianini N, Shawe-Taylor J. 支持向量机导论[M]. 李国正, 译. 北京: 电子工业出版社, 2004:82-105. [9] 丁世飞, 齐丙娟, 谭红艳, 等. 支持向量机理论与算法研究综述[J]. 电子科技大学学报, 2011, 40(1):2-10. [10] 刘畅, 孙德山. 模糊支持向量机隶属度的确定方法[J]. 计算机工程与应用, 2008, 44(11):41-42. [11] 王正帅, 邓喀中, 谭志祥. 导水裂缝带高度预测的模糊支持向量机模型[J]. 地下空间与工程学报, 2011, 7(4): 723-727. [12] 王欣, 李胜刚, 秦斌, 等. 基于模糊支持向量机的风电场功率预测[J]. 新型工业化, 2014(9):50-55. [13] Pan W T. A new fruit fly optimization algorithm: Taking the financial distress model as an example[J]. Knowledge- Based Systems, 2012, 26(2):69-74. [14] Zheng X, Wang L, Zheng H. A knowledge-based fruit fly optimization algorithm for multi-skill resource constrained project scheduling problem[J]. Soft Computing, 2017, 21(6):1537-1548. [15] Seghir F, Khababa A. A hybrid approach using genetic and fruit fly optimization algorithms for QoS-aware cloud service composition[J]. Journal of Intelligent Manufacturing, 2017(6):1-20. |
| 备注/Memo: | 收稿日期: 2018?05?22. 宁波大学学报（理工版）网址: http://journallg.nbu.edu.cn/ 基金项目: 国家自然科学基金（61471212）; 浙江省自然科学基金（LY16F010001）; 宁波市自然科学基金（2016A610091, 2017A610297）. 第一作者: 何彩芬（1974－）, 女, 浙江宁海人, 高级工程师, 主要研究方向: 短临、短期天气预报. E-mail: 468176571@qq.com *通信作者: 金炜（1969－）, 男, 浙江兰溪人, 教授, 主要研究方向: 压缩感知、模式识别和数字图像处理. E-mail: xyjw1969@126.com 宁波大学学报（理工版）网址：http://journallg.nbu.edu.cn/ |
