基于机器学习的雷电预报研究
|
摘要
高准确率的雷电预报,有助于降低雷电带来的灾害,从而减少雷电造成的损失,所以如何提高雷电预报准确率具有重要的现实意义。为了提高支持向量机(SVM)算法的分类效果,引入了灰狼优化算法(GWO),利用GWO算法的全局优化能力优化SVM的c和σ,从而提高SVM分类的准确性。由于采集的雷电数据属性较多,采用主成分分析(PCA)方法对属性进行约简,获得能够反映雷电情况的主要影响因子,作为GWO-SVM的输入数据,GWO-SVM的输出为雷电发生情况。最后建立了雷电预报仿真实验,实验对比结果现实,在相同的实验参数及实验数据情况下,GWO-SVM方法相比于传统的其他3种算法具有更高的雷电预报准确率;相比于前人所作研究,所提方法也具有更高的雷电预报准确率;验证了所提雷电预报方法的可靠性。
Lightning prediction with high accuracy can help to reduce the disaster and the the loss caused by lightning.Therefore,how to improve the accuracy of lightning prediction has important practical significance.In order to improve the classification effect of SVM algorithm,grey wolf optimization(GWO)algorithm is introduced.The global optimization ability of GWO algorithm was used to optimize c andσof the SVM,so as to improve the accuracy of SVM classification.Since there are many lightning data attributes collected,the PCA method is adopted to reduce the attributes,and the main influencing factors that can reflect the lightning conditions are obtained,which are used as the input data of GWO-SVM,and the output of GWO-SVM is the lightning occurrence.Finally,the simulation experiment of lightning prediction is established.The comparison results show that the GWO-SVM method has higher lightning prediction accuracy than the other three traditional algorithms under the same experimental parameters and data.Compared with previous researches,the method proposed in this paper also has higher accuracy of lightning prediction.The reliability of the lightning prediction method is verified.
Lightning prediction with high accuracy can help to reduce the disaster and the the loss caused by lightning.Therefore,how to improve the accuracy of lightning prediction has important practical significance.In order to improve the classification effect of SVM algorithm,grey wolf optimization(GWO)algorithm is introduced.The global optimization ability of GWO algorithm was used to optimize c andσof the SVM,so as to improve the accuracy of SVM classification.Since there are many lightning data attributes collected,the PCA method is adopted to reduce the attributes,and the main influencing factors that can reflect the lightning conditions are obtained,which are used as the input data of GWO-SVM,and the output of GWO-SVM is the lightning occurrence.Finally,the simulation experiment of lightning prediction is established.The comparison results show that the GWO-SVM method has higher lightning prediction accuracy than the other three traditional algorithms under the same experimental parameters and data.Compared with previous researches,the method proposed in this paper also has higher accuracy of lightning prediction.The reliability of the lightning prediction method is verified.
引文
[1]吕启深,贾逸伦,黄荣辉,等.基于空间密度聚类与LSSVM的雷云预测方法[J].电力科学与技术学报,2017,32(1):90-96.
[2]汪志红,王斌会,刘明.基于B样条曲线的GM(2,1)动态组合预测模型应用[J].中国安全科学学报,2011,21(7):157-162.
[3]路明月,张其林,骆兴江,等.基于GIS的雷电灾害监测预警与数据处理系统[J].气象科技,2010,38(6):832-837.
[4]佚名.LPS-1000雷电灾害风险预警系统[J].高电压技术,2013,39(9):2317.
[5]陈宇,王蕾,杨超,等.大连地区闪电活动时空特征分析及雷击风险度综合指数预测研究[J].气象科学,2017,37(6):832-838.
[6]田浩,章涵,冯万兴,等.基于BP神经网络和大气电场特征的地闪雷电预测方法[J].电瓷避雷器,2018(6):27-33.
[7]崔月生.基于PSO-BP算法的雷电流概率预测研究[J].国外电子测量技术,2018,37(10):118-123.
[8]高文胜,张博文,周瑞旭,等.基于雷电定位系统监测数据的雷暴云趋势预测[J].电网技术,2015,39(2):523-529.
[9]冯万兴,朱晔,郭钧天,等.基于改进的DBSCAN方法和多项式拟合的雷电短时预测[J].计算机工程与科学,2014,36(10):2028-2033.
[10]侯荣涛,路郁,王琴,等.OPTICS算法在雷电临近预报中的应用[J].计算机应用,2014,34(1):297-301.
[11]孙丽华,严军峰,徐健锋.基于多机器学习竞争策略的短时雷电预报[J].计算机应用,2016,36(9):2555-2559.
[12]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.
[13]刘爱国,薛云涛,胡江鹭,等.基于GA优化SVM的风电功率的超短期预测[J].电力系统保护与控制,2015,43(2):90-95.
[14]邓曾,李丹,柯樱海,等.基于改进SVM算法的高分辨率遥感影像分类[J].国土资源遥感,2016,28(3):12-18.
[15]单英浩,付青,耿炫,等.基于改进BP-SVM-ELM与粒子化SOM-LSF的微电网光伏发电组合预测方法[J].中国电机工程学报,2016,36(12):3334-3343.
[16]郭振洲,刘然,拱长青,等.基于灰狼算法的改进研究[J].计算机应用研究,2017,34(12):3603-3606,3610.
[17]邢尹,陈闯,刘立龙,等.求解函数最优解的改进灰狼算法[J].计算机仿真,2018,35(9):258-262.
[18]唐勇波,桂卫华,彭涛,等.PCA和KICA特征提取的变压器故障诊断模型[J].高电压技术,2014,40(2):557-563.
[19]彭永供,邱桃荣,林于渊,等.基于哈夫曼树的雷电数据采样算法[J].计算机工程,2013,39(5):174-177,182.
[2]汪志红,王斌会,刘明.基于B样条曲线的GM(2,1)动态组合预测模型应用[J].中国安全科学学报,2011,21(7):157-162.
[3]路明月,张其林,骆兴江,等.基于GIS的雷电灾害监测预警与数据处理系统[J].气象科技,2010,38(6):832-837.
[4]佚名.LPS-1000雷电灾害风险预警系统[J].高电压技术,2013,39(9):2317.
[5]陈宇,王蕾,杨超,等.大连地区闪电活动时空特征分析及雷击风险度综合指数预测研究[J].气象科学,2017,37(6):832-838.
[6]田浩,章涵,冯万兴,等.基于BP神经网络和大气电场特征的地闪雷电预测方法[J].电瓷避雷器,2018(6):27-33.
[7]崔月生.基于PSO-BP算法的雷电流概率预测研究[J].国外电子测量技术,2018,37(10):118-123.
[8]高文胜,张博文,周瑞旭,等.基于雷电定位系统监测数据的雷暴云趋势预测[J].电网技术,2015,39(2):523-529.
[9]冯万兴,朱晔,郭钧天,等.基于改进的DBSCAN方法和多项式拟合的雷电短时预测[J].计算机工程与科学,2014,36(10):2028-2033.
[10]侯荣涛,路郁,王琴,等.OPTICS算法在雷电临近预报中的应用[J].计算机应用,2014,34(1):297-301.
[11]孙丽华,严军峰,徐健锋.基于多机器学习竞争策略的短时雷电预报[J].计算机应用,2016,36(9):2555-2559.
[12]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.
[13]刘爱国,薛云涛,胡江鹭,等.基于GA优化SVM的风电功率的超短期预测[J].电力系统保护与控制,2015,43(2):90-95.
[14]邓曾,李丹,柯樱海,等.基于改进SVM算法的高分辨率遥感影像分类[J].国土资源遥感,2016,28(3):12-18.
[15]单英浩,付青,耿炫,等.基于改进BP-SVM-ELM与粒子化SOM-LSF的微电网光伏发电组合预测方法[J].中国电机工程学报,2016,36(12):3334-3343.
[16]郭振洲,刘然,拱长青,等.基于灰狼算法的改进研究[J].计算机应用研究,2017,34(12):3603-3606,3610.
[17]邢尹,陈闯,刘立龙,等.求解函数最优解的改进灰狼算法[J].计算机仿真,2018,35(9):258-262.
[18]唐勇波,桂卫华,彭涛,等.PCA和KICA特征提取的变压器故障诊断模型[J].高电压技术,2014,40(2):557-563.
[19]彭永供,邱桃荣,林于渊,等.基于哈夫曼树的雷电数据采样算法[J].计算机工程,2013,39(5):174-177,182.