日气温多元时间序列局部支持向量回归预测

系统仿真学报 ›› 2016, Vol. 28 ›› Issue (3): 654-660.

日气温多元时间序列局部支持向量回归预测

王定成, 曹智丽, 陈北京, 倪郁佳

南京信息工程大学计算机与软件学院,南京 210044

收稿日期:2014-10-27 修回日期:2015-01-11 发布日期:2020-07-02
作者简介:王定成(1967-),男,安徽霍山,博士,研究员,研究方向为智能计算;曹智丽(1989-),女,江苏常州,硕士,研究方向为智能计算。
基金资助:
国家自然科学基金(61103141);江苏省自然科学基金(BK2012858)

Multivariate Time Series Local Support Vector Regression Forecast Methods for Daily Temperature

Wang Dingcheng, Cao Zhili, Chen Beijing, Ni Yujia

College of Computer and Software, Nanjing University of Information Science and Technology, Nanjing 210044, China

Received:2014-10-27 Revised:2015-01-11 Published:2020-07-02

摘要/Abstract

摘要： 气温预报是天气预报的重要因素之一,但大气系统是一个复杂的非线性系统,要提高预报精度,需要探索新的预报方法。研究一种多元时间序列局部支持向量回归的日气温预测方法,以日最高、最低气温为例,使用C-C方法和最小预测误差法构造日最高、最低气温的多元时间序列,将分段提取最近邻点的方法应用于局部支持向量回归,建立提前1天的每日最高、最低气温局部预测模型。以中国753站资料包中的数据进行仿真实验,与欧氏距离提取最近邻点相比,分段提取最近邻点的方法能有效提高日气温的预测精度。多元时间序列局部预测模型在日气温的短期预测(10天以内)上比单元时间序列有着更好的应用价值。

关键词: 日气温预测, 多元时间序列, 分段, 最近邻点, 局部支持向量回归

Abstract: Daily temperature forecast is an important part in weather forecasting. New methods are explored to improve the prediction accuracy since the atmosphere system is a complex nonlinear system. A model based on multivariate time series and local support vector regression was proposed. After constructing multivariate time-series with C-C method and minimum prediction error method, a way to extract the nearest neighbor from each predictor's sequences was used to build the 1-day ahead local forecasting model for daily maximum and minimum temperature. To demonstrate the effectiveness, the model was applied and tested in data from 753 stations data package of China. Simulation results show that the model can improve prediction accuracy effectively, and has a better application value in short-term daily temperature forecast compared with univariate time series.

Key words: daily temperature, multivariate time series, segmentation, nearest neighbor, local support vector regression

中图分类号:

TP391.9

王定成, 曹智丽, 陈北京, 倪郁佳. 日气温多元时间序列局部支持向量回归预测[J]. 系统仿真学报, 2016, 28(3): 654-660.

Wang Dingcheng, Cao Zhili, Chen Beijing, Ni Yujia. Multivariate Time Series Local Support Vector Regression Forecast Methods for Daily Temperature[J]. Journal of System Simulation, 2016, 28(3): 654-660.

参考文献

[1] Narendra Babu C, B Eswara Reddy. Predictive Data Mining on Average Global Temperature Using Variants of ARIMA models[C]// IEEE, Advances in Engineering, Science and Management. USA: IEEE, 2012: 75-80.
[2] 金志凤, 符国槐, 黄海静, 等. 基于BP 神经网络的杨梅大棚内气温预测模型研究[J]. 中国农业气象, 2011, 32(3): 362-367.
[3] Shipra Banik, Mohammed Anwer.Soft Computing Models to Predict Daily Temperature of Dhaka[C]// IEEE, Computer and Information Technology. USA: IEEE, 2010: 256-260.
[4] 张颖超, 郭栋, 熊雄. 自动站气温数据异常的补偿方法[J]. 计算机应用, 2014, 34(3): 888-891, 897.
[5] 张宜阳, 卢继平, 孟洋洋. 基于经验模式分解和混沌相空间重构的风电功率短期预测[J]. 电力系统自动化, 2012, 36(5): 24-28.
[6] 朱志宇, 姜长生, 张冰. 基于支持向量回归的混沌序列预测方法[J]. 电工技术学报, 2005, 20(6): 57-61.
[7] 行鸿彦, 龚平, 徐伟. 嵌入窗方法确定混沌系统重构参数的仿真研究[J]. 系统仿真学报, 2013, 25(6): 1219-1225.
(Xing Hongyan, Gong Ping, Xu Wei.Simulation Research of Chaos System Reconstruction Parameters Based on Embedded Window[J]. Journal of System Simulation (S1004-731X), 2013, 25(6): 1219-1225.)
[8] 陆振波, 蔡志明, 姜可宇, 等. 基于改进的C-C方法的相空间重构参数选择[J]. 系统仿真学报, 2007, 19(11): 2527-2529, 2538.
(Lu Zhenbo, Cai Zhiming, Jiang Keyu.Determination of Embedding Parameters for Phase Space Reconstruction Based on Improved C-C Method[J]. Journal of System Simulation (S1004-731X), 2007, 19(11): 2527-2529, 2538.)
[9] 黄磊, 舒杰, 姜桂秀. 基于多维时间序列局部支持向量回归的微网光伏发电预测[J]. 电力系统自动化, 2014, 38(5): 19-24.
[10] Vapnik V N.The nature of statistical learning theory[M]. New York, USA: Springer, 1995: 280-292.
[11] 尹传环, 牟少敏, 田盛丰. 局部支持向量机的研究进展[J]. 计算机科学, 2012, 39(1): 170-174.
[12] 唐贤伦, 李洋, 李鹏. 多智能体粒子群优化的SVR 模型预测控制[J]. 控制与决策, 2014, 29(4): 593-598.