基于决策树的EPG体验异常原因定位

doi:10.11959/j.issn.1000-0801.2019087

Abstract

Abstract:

Improving user experience has always been the focus of IPTV operation.However,IPTV network is relatively complex,including multiple scheduling links such as set-top box,access network,EPG page,EPG server and media server.Once the abnormality occurs,monitoring indicators of each link will be checked to locate the cause of abnormality by human experience.The operation mode relies on professionals,which is inefficient and unable to stop losses quickly.Thus,to solve the problem above,based on big data technology,decision tree was implied to locate the cause of abnormality according to the classification rule of the tree model.Decision tree model has been used in actual networks of IPTV and helps to find out the cause of abnormality,which improves the efficiency of operation.

Key words: IPTV, decision tree, big data, AIOps

CLC Number:

TP393

Xiaomin TAN,Ai FANG,Bing LIANG,Haojie YANG. Locating causes of abnormality of EPG experience based on decision tree[J]. Telecommunications Science, 2019, 35(8): 158-164.

Figures/Tables 7

References 13

[1]	黄晓波, 黄志武, . IPTV视频质量故障定位及处理方法[J]. 信息通信, 2010(4): 67-68.
	HUANG X B , HUANG Z W , . IPTV video quality fault location and processing method[J]. Information and Communications, 2008,24(4): 67-68.
[2]	刘奇峰, . 基于大数据的 IPTV 故障定位系统的设计与实现[J]. 南京:南京邮电大学, 2017.
	LIU Q F , . Design and implementation of IPTV fault location system based on big data[J]. Nanjing: Nanjing University of Posts and Telecommunications, 2017.
[3]	姚良, 肖晴, 陈文 . IPTV机顶盒内置质量监测工具的开发与应用[J]. 电信科学, 2008,24(11): 80-83.
	YAO L , XIAO Q , CHEN W . Development and application of built-in quality monitoring tool of IPTV set-top box[J]. Telecommunications Science, 2008,24(11): 80-83.
[4]	陈舒 . 基于多协议层QoS参数关联的IPTV故障点定位方法[J]. 电视技术, 2013,37(12): 55-58.
	CHEN S . Method of IPTV fault isolation based on correlated analysis of multi-protocol-layer QoS parameter[J]. Video Engineering, 2013,37(12): 55-58.
[5]	吴志峰 . 基于数据挖掘的IPTV 故障诊断研究与实现[D]. 南京:南京邮电大学, 2017.
	WU Z F . The research and implement of IPTV fault diagnosis based on data mining[D]. Nanjing:Nanjing University of Posts and Telecommunications, 2017.
[6]	QIAN Y , WEI X , HUANG R ,et al. Fault prediction in IPTV using improved AdaBoost algorithm[C]// International Conference on Wireless Communications ＆ Signal Processing,Oct 13-15,2016,Yangzhou,China. Piscataway:IEEE Press, 2016: 1-5.
[7]	王泽, 屈海伟 . 大数据分析在IPTV维护中的应用[J]. 电信技术, 2014,1(10).
	WANG Z , QU H W . Application of big data analysis in IPTV maintenance[J]. Telecommunications Technology, 2014,1(10).
[8]	CHEN T , GUESTRIN C . XGBoost:a scalable tree boosting system[Z].2016. 2016.
[9]	张琳, 陈燕, 李桃迎 ,等. 决策树分类算法研究[J]. 计算机工程, 2011,37(13): 66-67.
	ZHANG L , CHEN Y , LI T Y ,et al. Research on decision tree classification algorithms[J]. Computer Engineering, 2011,37(13): 66-67.
[10]	周志华 . 机器学习[M]. 北京: 清华大学出版社, 2016.
	ZHOU Z H . Machine learing[M]. Beijing: Tsinghua University PressPress, 2016.
[11]	STEINBERG D , COLLA P . CART:classification and regression trees[J]. The Top Ten Algorithms in Data Mining, 2009(9):179.
[12]	MORE A . Survey of resampling techniques for improving classification performance in unbalanced datasets[J]. 2016 arXiv:1608.06048.,
[13]	熊冰妍, 王国胤, 邓维斌 . 基于样本权重的不平衡数据欠抽样方法[J]. 计算机研究与发展, 2016,53(11): 2613-2622.
	XIONG B Y , WANG G Y , DENG W B . Under-sampling method based on sample weight for imbalanced data[J]. Journal of Computer Research and Development, 2016,53(11): 2613-2622.

Metrics

Recommended 0

No Suggested Reading articles found!

样本类别	预测为正常1	预测为异常0
正常1	true positive（TP）	false negative（FN）
异常0	false positive（FP）	true negative（TN）

用户账号	EPG服务器	机顶盒型号	访问页面	加载时间
用户1	IP1	ZXT*	首页tab1	7 012 ms
用户2	IP1	FIBER*	首页tab2	801 ms
用户3	IP2	EC6108V*	首页tab2	423 ms

样例	类别	精确率	召回率	F1值
mm527	异常	0.05	0.91	0.1
	正常	1.00	0.73	0.84
zq521	异常	0.09	0.84	0.16
	正常	0.99	0.71	0.83
yj514	异常	0.11	0.88	0.19
	正常	0.99	0.76	0.86
cz507	异常	0.07	0.81	0.12
	正常	0.99	0.76	0.86
hy507	异常	0.05	0.84	0.10
	正常	1.00	0.77	0.87
jm507	异常	0.15	0.88	0.26
	正常	1.00	0.93	0.96
jy507	异常	0.01	0.70	0.01
	正常	1.00	0.69	0.81
mm507	异常	0.22	0.86	0.35
	正常	1.00	0.94	0.97
mz507	异常	0.04	0.72	0.08
	正常	1.00	0.80	0.89
st507	异常	0.04	0.81	0.07
	正常	1.00	0.75	0.85
yj507	异常	0.13	0.83	0.22
	正常	1.00	0.93	0.96

[1]	Lu HAN, Weiyu CHEN, Fei ZHANG, Jianfeng HE, Huaizhen SU. Big data classification method of non relational distributed submission information under differentiated requirements [J]. Telecommunications Science, 2023, 39(6): 114-121.
[2]	Xue HAN. Damage toughness assessment method of power backbone communication network based on power big data [J]. Telecommunications Science, 2023, 39(5): 136-143.
[3]	Xuerong WANG, Zhengzhi TANG, Yinchuan LI, Meiyu QI, Jianbo ZHU, Liang ZHANG. Delay-sensitive traffic intellisense scheduling based on optimal decision tree [J]. Telecommunications Science, 2023, 39(4): 120-132.
[4]	Yudi SUN. A prediction model of massive 5G network users’ revisit behavior based on telecom big data [J]. Telecommunications Science, 2023, 39(2): 157-162.
[5]	Aihua LI, Xiaobo WU, Chao CHEN, Bin WEI, Yuanyuan SHI. Big data intelligent analysis technology for 5G network [J]. Telecommunications Science, 2022, 38(8): 129-139.
[6]	Gengsheng HUANG, Yuhong HUANG, Manxue GUO, Jianping ZHENG, Xin GE. Architecture of a new infrastructure for data service in DT era [J]. Telecommunications Science, 2022, 38(7): 138-145.
[7]	Panpan LI, Zhengxia XIE, Guangxue YUE, Xin LIU. Research progress and trends of deep learning based wireless communication receiving method [J]. Telecommunications Science, 2022, 38(2): 1-17.
[8]	Haibo ZHAO, Zhijun XIANG, Linsong XIAO. A big data framework for short-term power load forecasting using heterogenous data [J]. Telecommunications Science, 2022, 38(12): 103-111.
[9]	Jian HU, Lei SUN, Yiyan YIN, Xiaokang YANG, Jingui BAI, Yejiang ZHANG. Research on 4G/5G voice quality optimization based on data mining and geographic visualization [J]. Telecommunications Science, 2022, 38(10): 131-139.
[10]	Zhiyong LIU, Zhongjiang HE, Yilong RUAN, Junfeng SHAN, Chao ZHANG. Big data security features and operation practices [J]. Telecommunications Science, 2021, 37(5): 160-169.
[11]	Gang LU,Changyi CHEN,Zelong HUANG,Zeyuan HUANG. Research on intelligent cloud native architecture and key technologies for cloud and network integration [J]. Telecommunications Science, 2020, 36(9): 67-74.
[12]	Xiaojun LIU,Juan WU,Xiaoqing XU. Big data architecture analysis and data security fusion technology [J]. Telecommunications Science, 2020, 36(7): 146-155.
[13]	Yujiao LIU,Kunhuang SONG,Xiang WANG. Analysis of economic prosperity index based on big data of electricity [J]. Telecommunications Science, 2020, 36(6): 166-171.
[14]	Long XUE,Gang LU,Qi ZHOU,Huiyan ZHANG,Tingjun WAN. Cloud native intelligent operation and maintenance technology [J]. Telecommunications Science, 2020, 36(12): 105-112.
[15]	Weihua CHENG,Xiaorong HE. Quality analysis method of Web browsing based on big data [J]. Telecommunications Science, 2020, 36(11): 174-181.

Locating causes of abnormality of EPG experience based on decision tree

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 13

Related Articles 15

Metrics

Recommended 0