基于改进随机森林算法的电力业务实时流量分类方法

为了更有效地对电力业务系统安全接入过程中日渐增多的流量进行实时分类,提高电力系统的业务处理速度,提出了一种基于改进随机森林算法的电力业务实时流量分类方法。在分析电力业务安全接入实时流量特征的基础上,改进传统随机森林算法,基于分类间隔加权对随机森林进行修剪来提高分类实时性;对新的样本数据进行数据剪辑来提高分类的准确性。在此改进算法的基础上设计了电力业务安全接入实时流量分类流程。最后以某省电力公司安全接入实时流量分类为例,验证了所提方法的准确性和实时性。...

Full description

Saved in:
Bibliographic Details
Published in电力系统保护与控制 Vol. 44; no. 24; pp. 82 - 89
Main Author 许勇刚 张建业 龚小刚 姜珂 周欢 殷继英
Format Journal Article
LanguageChinese
Published 北京中电普华信息技术有限公司,北京,100085%国网新疆电力公司,新疆 乌鲁木齐,830018%国网浙江电力公司,浙江 杭州,310007%华北电力大学控制与计算机工程学院,北京,102206%国家开发投资公司,北京,100034 2016
Subjects
分类间隔
数据剪辑
流量分类
电力业务
随机森林
classification margin
流量分类
随机森林
power business
数据剪辑
random forests
分类间隔
电力业务
data editing
traffic classification
Online AccessGet full text
ISSN1674-3415
DOI10.7667/PSPC152144

Cover

More Information
Summary:为了更有效地对电力业务系统安全接入过程中日渐增多的流量进行实时分类,提高电力系统的业务处理速度,提出了一种基于改进随机森林算法的电力业务实时流量分类方法。在分析电力业务安全接入实时流量特征的基础上,改进传统随机森林算法,基于分类间隔加权对随机森林进行修剪来提高分类实时性;对新的样本数据进行数据剪辑来提高分类的准确性。在此改进算法的基础上设计了电力业务安全接入实时流量分类流程。最后以某省电力公司安全接入实时流量分类为例,验证了所提方法的准确性和实时性。
Bibliography:random forests; data editing; classification margin; power business; traffic classification
XU Yonggang;ZHANG Jianye;GONG Xiaogang;JIANG Ke;ZHOU Huan;YIN Jiying;（1. Beijing China Power Information Technology Co., Ltd., Beijing 100085, China; 2. State Grid Xinjiang Electric Power Co., Wulumuqi 830018, China; 3. State Grid Zhejiang Electric Power Co., Hangzhou 310007, China; 4. School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China; 5. State Development Investment Co., Beijing 100034, China）
This paper aims to classify the growing number of real-time traffic during the secure access process of the power business system more effectively and to improve the speed of business processing of the power system. A real-time traffic classification method of the power business based on improved random forests algorithm is proposed. On the basis of analyzing characteristics of real-time traffic in secure access of the power business, traditional random forests algorithm is im
ISSN:1674-3415
DOI:10.7667/PSPC152144