基于改进的DBSCAN方法和多项式拟合的雷电短时预测

J4 ›› 2014, Vol. 36 ›› Issue (10): 2028-2033.

基于改进的DBSCAN方法和多项式拟合的雷电短时预测

冯万兴1，朱晔1，郭钧天1，张晓庆2，刘娟2

（1.国网电力科学研究院，湖北武汉 430074；2.武汉大学计算机学院，湖北武汉 430072）

收稿日期:2014-06-15 修回日期:2014-08-20 出版日期:2014-10-25 发布日期:2014-10-25
基金资助:
国家自然科学基金资助项目（61272274）

Lightning forecast based on the improved
DBSCAN and polynomial fitting

FENG Wanxing1，ZHU Ye1，GUO Juntian1，ZHANG Xiaoqing2，LIU Juan2

（1.State Grid Electric Power Research Institute,Wuhan 430074;
2.School of Computer,Wuhan University,Wuhan 430072,China）

Received:2014-06-15 Revised:2014-08-20 Online:2014-10-25 Published:2014-10-25

摘要/Abstract

摘要：

结合雷电数据自身特征改进DBSCAN方法，提出了一种基于DBSCAN和多项式拟合的雷电预测方法，提高预测的准确性。首先对某一时间段内的雷电数据按密度进行聚类并将每类所有雷电数据的平均坐标作为该类的中心点；然后在下一个时间段使用上一时间段的中心点作为初始选择点进行DBSCAN聚类，重复上述过程直到所有历史数据处理完毕，得到一系列不同时间段不同类别的雷电中心点；最后使用多项式拟合预测接下来的雷电可能发生的中心位置。对雷电监测网提供的雷电数据进行测试，结果表明，在数据充分的情况下，基于DBSCAN方法和多项式拟合的雷电预测准确率较令人满意，实际雷电中心点与预测中心点坐标误差约为0.1(±0.1)。

关键词: 雷电预测, DBSCAN方法, 多项式拟合

Abstract:

Using the improved DBSCAN algorithm considering the original characteristics of the lightning data,a lightning forecast method based on the improved DBSCAN and polynomial fitting is proposed to improve the prediction accuracy.Firstly,the lightning data during a span of time is clustered according to the density, and the average coordinates of all of the lightning data are designated as the central points of the cluster. Secondly,the central points in the last span of time are chosen as the initial selection points in the current span of time to perform DBSCAN clustering. The twostep procedure is iterated until all history data are processed. Finally, the polynomial fitting method is used to process the central location of each category.After dealing with the data provided by the Lightning Detection Network, the estimated and the observed performance data are presented and compared.The results are encouraging since the deviation between the actual data and the forecasted data is around 0.1 in most situations.

Key words: lightning forecast;DBSCAN;polynomial fitting

冯万兴1，朱晔1，郭钧天1，张晓庆2，刘娟2. 基于改进的DBSCAN方法和多项式拟合的雷电短时预测[J]. J4, 2014, 36(10): 2028-2033.

FENG Wanxing1，ZHU Ye1，GUO Juntian1，ZHANG Xiaoqing2，LIU Juan2. Lightning forecast based on the improved
DBSCAN and polynomial fitting [J]. J4, 2014, 36(10): 2028-2033.

参考文献［11］

［1］	Zhang Yijun, Zhou Xiuji．Review and progress of lightning research［J］. Journal of Applied Meteorological Science,2006, 17(6):829834. (in Chinese)
［2］	Avila A F, Lopes I J S, Miranda G C．The application of the lightning locating system data to analyze lightning preformance distribution lines in Minas Gerais State［C］∥Proc of the IEEE Transmission Distribution Conference and Exposition, 2006:1.
［3］	Cheng Fei,Wang Xiaohong,Wang Xinjiang.A study of statistical relationship between the humidity of atmosphere and the thunderstorms weather［J］. Information Technology and Informatization, 2011(1):4851. (in Chinese)
［4］	Zhao Xuhuan, Wang Zhenhui, Xiao Wenan, et al. A preliminary study of neural network based shortterm thunderstorm forecast［J］. Journal of Tropical Meteorology,2009, 25(3):357360. (in Chinese)
［5］	You Zhiyuan,Gu Chenghua,Li Xiangchao,et al.The study on the characteristics of lightning based on BP neural network and data mining［C］∥Proc of the 7th Yangtze River Delta Forum on Science & Technology,2010:432437. (in Chinese)
［6］	Nathiya G，Punitha S C，Punithavalli D M.An analytical study on behavior of clusters using k means, em and k* means algorithm［J］.International Journal of Computer Science and Information Security, 2010, 7(3):185190.
［7］	Geng Xuehua, Fu Desheng. Research on visual data mining technique［J］. Computer Applications and Software, 2006, 23(2): 8587. (in Chinese)
［8］	Qian Weining, Gong Xueqing, Zhou Aoying．Clustering in very large databases based on distance and density［J］．Journal of Computer Science and Technology, 2003, 18(1):6776.
［9］	He Li. Prediction method of user browsing behaviors based on classified Markov chain［J］. Computer Engineering, 2008, 34(22):3233. (in Chinese)
［10］	Xiu Chunbo.Onestep prediction method for time series based on chaotic operator network［J］. Journal of System Simulation, 2009, 21(2):507509. (in Chinese)
［11］	Tan Hua.Study the exchange rate forecasting method based on streaming data mining［J］. Journal of Xiangnan University, 2010, 31(4):2729. (in Chinese)
［12］	Ester M, Kriegel HP, Sander J, et al．A densitybased algorithm for discovering clusters in large spatial databases with noise［C］∥Proc of International Conference on Knowledge Discovery and Data Mining, 1996:226231.
	附中文参考文献：
［1］	张义军, 周秀骥．雷电研究的回顾和进展［J］. 应用气象学报,2006，17(6):829834.
［3］	程飞，王孝红,王新江. 大气相对湿度与雷暴天气的统计关系研究［J］. 信息技术与信息化，2011(1):4851.
［4］	赵旭寰，王振会，肖稳安,等. 神经网络在雷暴预报中的应用初步研究［J］. 热带气象学报，2009，25(3):357360.
［5］	游志远，顾承华,李祥超，等. 基于BP神经网络数据挖掘技术的雷电特征研究［C］∥第七届长三角科技论坛能源分论坛长三角气象科技论坛，2010：432437.
［7］	耿学华，傅德胜．可视化数据挖掘技术研究［J］．计算机应用与软件，2006，23(2)：8587.
［9］	何丽．基于类Markov链的用户浏览行为预测方法［J］．计算机工程,2008,34（22）：3233.
［10］	修春波．基于混沌算子网络的时间序列一步预测方法［J］．系统仿真学报,2009,21（2）：507509.
［11］	谭华．流式数据挖掘方法下的汇率行为预测方法探讨［J］．湘南学院学报,2010,31（4）：2729.