CN114124676A - 一种面向网络智能运维系统的故障根因定位方法及其系统 - Google Patents

一种面向网络智能运维系统的故障根因定位方法及其系统 Download PDF

Info

Publication number
CN114124676A
CN114124676A CN202111375636.0A CN202111375636A CN114124676A CN 114124676 A CN114124676 A CN 114124676A CN 202111375636 A CN202111375636 A CN 202111375636A CN 114124676 A CN114124676 A CN 114124676A
Authority
CN
China
Prior art keywords
data
root cause
data set
sample
fault
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202111375636.0A
Other languages
English (en)
Other versions
CN114124676B (zh
Inventor
徐小龙
徐诗成
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Posts and Telecommunications
Original Assignee
Nanjing University of Posts and Telecommunications
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing University of Posts and Telecommunications filed Critical Nanjing University of Posts and Telecommunications
Priority to CN202111375636.0A priority Critical patent/CN114124676B/zh
Publication of CN114124676A publication Critical patent/CN114124676A/zh
Application granted granted Critical
Publication of CN114124676B publication Critical patent/CN114124676B/zh
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/06Management of faults, events, alarms or notifications
    • H04L41/0677Localisation of faults
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/21Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14Network analysis or design
    • H04L41/145Network analysis or design involving simulating, designing, planning or modelling of a network
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04SSYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
    • Y04S10/52Outage or fault management, e.g. fault detection or location

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Test And Diagnosis Of Digital Computers (AREA)
  • Telephonic Communication Services (AREA)

Abstract

一种面向网络智能运维系统的故障根因定位方法,包括如下步骤:首先将不平衡数据进行划分,抽取少类的样本数据;然后将少类样本利用生成对抗网络来进行数据增强来生成合成数据,并通过计算合成数据和原始数据之间的损失来判断生成效果对生成器进行反馈;然后将生成效果好的合成数据与原始数据进行合并生成整合数据;最后将整合数据输入到根因分类模型中进行模型的训练,将可能为根因的样本标记并最终输出。本发明能够充分利用故障数据来提取数据之间的关系,并能够使生成的数据拥有根因数据的原始特征和潜在空间中的数据分布、隐藏模式,在对准确率、F1值要求较高的故障根因定位系统中具有良好的实用性。

Description

一种面向网络智能运维系统的故障根因定位方法及其系统
技术领域
本发明属于网络运维领域,具体涉及一种面向网络智能运维系统的故障根因定位方法及其系统。
背景技术
网络拓扑环境下故障的根因定位在现代运维中非常重要,且一直是运维领域重点研究方向。近年来,在通信行业中提出了智能告警解决了部分故障管理的相关问题,但在目前的状态下绝大多数基于异常检测根因分析的故障定位仍然准确率不高,导致派单任务指定错误造成经济人力成本的增加以及运维效率降低。在异常中进行根因分析定位故障作为智能网络运维的一个关键环节,能够加快网络运维快速解决问题,使得服务器正常运行,有效解决故障所造成的问题。
随着大数据时代的到来和机器学习、深度学习等技术的快速发展,人们可以在强大算力的支持下,利用复杂的神经网络模型挖掘和提取海量数据中的关键信息。尤其在复杂的异构网络环境中,成千上万的网络节点每天会产生大量的网络运行信息,当一个节点出现故障,往往会导致与其相连的其他节点也发生异常,进而产生大量告警,将真正根因淹没掉,甚至会导致网络的瘫痪。这造成了故障根因定位存在数据极度不平衡问题,即故障数据较多、标注根因数据较少,即训练样本较少,从而导致模型偏向性显著,产生过拟合问题,模型泛化能力弱。当出现大量告警时,为保证服务的稳定运行,我们需要对这些告警进行分析处理,而如何在告警风暴时压缩告警,快速过滤掉无效的告警,然后准确定位出可能的疑似根因节点成为诊断网络故障的当务之急。
目前故障根因分析方法主要分为两类:基于领域知识和数据驱动(data-driven)。
(1)基于领域知识,其中一些研究工作集中关注一种基于配置管理数据库和故障规则推理的故障树分析方法,该方法结合了专家规则系统和推理引擎,需要包括运维人员的经验知识等深入的领域知识,这些知识(特别是经验知识、规则)通常难以维护和更新。当数据量较小时,基于规则的根因分析方法尚且有效,但当数据量不断增长以后,规则的泛化能力则会逐渐变弱。还有一些研究工作集中在基于故障传播图的根因分析方法上,通过系统依赖图来推断多级依赖关系实现高度可靠的网络服务。缺点是要求精确的条件概率。
(2)基于数据驱动,其中一些研究工作集中在通过监督学习的根因分析方法来学习历史标记数据得到分类模型从而预测系统当前的根源异常,缺点由于根因标记数据较少,导致数据极度不平衡,容易造成过拟合问题,使得训练的模型泛化能力较弱,在更多样化的数据其表现欠佳。还有一些研究工作集中在通过无监督学习的根因分析方法从数据中挖掘系统组件之间的内在关系进而推断根因。
发明内容
本发明的目:为解决现有技术中存在的问题,本发明提供一种面向网络智能运维系统的故障根因定位方法及系统,利用数据驱动的优势,融合生成对抗网络的优点,实现不平衡数据的数据增强,并对网络故障根因进行分类、定位。
一种面向网络智能运维系统的故障根因定位方法,包括以下步骤:
步骤1,将已经过标记的不平衡故障根因数据进行数据的划分,从中筛选出类别为少类的样本数据,即标签为1,将其作为源数据集S1,另一类样本,即标签为0,将其作为源数据集S2;
步骤2,采用生成对抗网络模型,首先利用生成器对源数据集S1进行数据的生成,再利用判别器对生成的数据进行损失计算,得到合成数据,将其作为合成数据集T;
步骤3,采将源数据集S1、源数据集S2和合成数据集T进行整合形成最终的整合数据集Q,并将其划分为训练集M和测试集N;
步骤4,用训练集M构建并训练根因分类器,对测试集N进行预测,根因分类器输出测试集N中可能的故障根因;
步骤5,利用根因分类器的输出对测试集N中所有实例进行标记,得到标记结果c,所述标记结果c的标记值为0时,表示实例非故障根因,标记值为1时,表示实例为故障根因;
步骤6:根据标记结果c,输出故障根因。
进一步地,所述步骤2中的生成器采用编码器-解码器-编码器子网模型,其中两个编码器分别学习获取输入样本表示和生成样本表示,解码器尝试重构输入数据;将噪音数据X馈入第一个编码器Encoder1,Encoder1是由卷积层、批处理范数、LeakReLU激活函数组成;Encoder1将输入数据X转换成潜在表示,是Decoder用来重构输入数据的样本;Decoder是由卷积转置层、LeakReLU激活函数和批处理范数组成;第二个编码器Encoder2的网络结构与Encoder1相同,但参数不同,输出在数据维度上与相同;生成器的损失函数是通过式(1)三种损失函数之和来指示生成器:
L=ωfLfaLabLb (1)
式(1)中,Lf是差异损失,通过生成的样本输入判别器,根据判别器的输出来计算;La是表观损失,Lb是潜在损失,以最小化真实样本的潜在表示和生成样本的编码瓶颈特征之间的距离;ωf、ωa和ωb为超参数;
采用式(1)来指示生成器;
判别器的损失函数是通过式(2)来指示判别器:
Figure BDA0003363889680000041
式(2)中PG(x)表示生成数据分布,Pdata(x)表示真实数据分布,
Figure BDA0003363889680000042
Figure BDA0003363889680000043
代表两个数据分布的期望值;fw表示判别器,α表示正则项,
Figure BDA0003363889680000044
表示梯度惩罚项,
Figure BDA0003363889680000045
表示整个样本空间,其分布可由以下步骤得到:
随机选取一个真实样本xi、一个生成样本
Figure BDA0003363889680000046
一个[0,1]随机数ε;
得到插值样本
Figure BDA0003363889680000047
由式(3)表示:
Figure BDA0003363889680000048
多个插值样本构成的分布,记作
Figure BDA0003363889680000049
进一步地,所述步骤5中采用式(4)计算得到标记结果c:
Figure BDA00033638896800000410
式(4)中,
Figure BDA00033638896800000411
为样本k的第i个特征,D为所有可用于模型训练的数据集,Dk为D中的子集,yj为样本j的特征值,a为参数,p为先验值。
一种面向网络智能运维系统的故障根因定位系统,包括:
数据集划分模块,用于对从不平衡数据集中筛选出少类样本所形成的源数据集S1和多类样本所形成的源数据集S2;
生成对抗网络模型模块,用于对源数据集S1进行数据增强,以此生成高质量的合成数据,作为合成数据集T;
生成器:用于生成合成数据,以输入给判别器进行判别;
判别器:用于判别是原始数据还是合成数据,并计算二者之间的损失;
根因分类器,用于对测试集N进行预测,输出测试集N中每个实例故障根因;
标记模块,用于对测试集N中所有实例进行标记,得到标记结果;
显示模块,用于根据标记结果,定位并显示网络中的故障根因。
进一步地,生成对抗网络模型模块中,生成合成数据T并与源数据集S1和源数据集S2合并构成整合数据集Q。
进一步地,采用整合数据集Q构建根因分类器。
本发明具有以下有益效果:
(1)针对网络中的故障根因定位,利用数据驱动的优势,融合生成对抗网络的优点。本方法能够充分利用故障数据来提取数据之间的关系,并能够使生成的数据拥有根因数据的原始特征和潜在空间中的数据分布、隐藏模式,公开数据上都取得优异的效果,在对准确率、F1值要求较高的故障根因定位系统中具有良好的实用性。
(2)本方法中利用生成对抗网络来拟合学习少类数据的分布,有效减小生成的少类样本与其他样本之间重叠的可能性,且能很好地拟合高维数据的分布,解决了该标注数据的不平衡问题,并从数据层面出发,将非结构化数据的数据增强算法成功迁移到了结构化数据。
(3)本方法中生成器采用了编码器-解码器-编码器三个子网络,这使得在生成器模型中能够生成更高质量的数据,以此提高分类模型的分类效果以及泛化能力。
(4)本方法中增加了生成器输入噪声的多样性,并在判别器的损失函数中引入了引入梯度惩罚,从而克服结构化数据训练困难、不稳定等问题。
(5)本方法算法结构简单,时间复杂度低。
附图说明
图1是本发明实施例中设计的面向网络智能运维系统的故障根因定位方法的流程示意图。
图2是本发明实施例中生成对抗网络模型图。
图3是本发明实施例中故障根因定位系统结构图。
具体实施方式
下面结合说明书附图对本发明的技术方案做进一步的详细说明。
如图1所示,本发明的一种面向网络智能运维系统的故障根因定位方法,针对网络中的故障根因定位,利用数据驱动的优势,融合生成对抗网络的优点。包括如下步骤:首先将不平衡数据进行划分,抽取少类的样本数据;然后将少类样本利用生成对抗网络来进行数据增强来生成合成数据,并通过计算合成数据和原始数据之间的损失来判断生成效果对生成器进行反馈;然后将生成效果好的合成数据与原始数据进行合并生成整合数据;最后将整合数据输入到根因分类模型中进行模型的训练,将可能为根因的样本标记并最终输出。该方法能够充分利用故障数据来提取数据之间的关系,并能够使生成的数据拥有根因数据的原始特征和潜在空间中的数据分布、隐藏模式,公开数据上都取得优异的效果,在对准确率、F1值要求较高的故障根因定位系统中具有良好的实用性。
本实施例的跨项目软件缺陷预测方法,用于针对目标软件项目进行缺陷预测,实际应用过程当中,具体包括如下步骤:
步骤1:将已经过专家标记的不平衡故障根因数据进行数据的划分,从中筛选出类别为少类的样本数据(即标签为1),将其作为源数据集S1,另一类样本(即标签为0)将其作为源数据集S2。对源数据集S1、S2分别做预处理后各自得到包含sys_id、time、node_id等总共64个脱敏变量,分别用A1、...、A64表示,部分样例如表1所示:
表1部分样例示例表
Figure BDA0003363889680000071
Figure BDA0003363889680000081
其中所选数据中的各标签计数如表2所示
表2原数据集标签统计表
Figure BDA0003363889680000082
注:标签0代表非根因,标签1代表是根因。
步骤2:按如下设计,采用用生成对抗网络模型对源数据集S1进行数据增强,首先利用生成器对源数据集S1进行数据的生成,再利用判别器对生成的数据进行损失计算,得到效果较好的合成数据,将其作为合成数据集T;
其中生成器采用编码器-解码器-编码器子网模型,其中两个编码器分别学习获取输入样本表示和生成样本表示,解码器尝试重构输入数据。将噪音数据X馈入第一个编码器Encoder1,Encoder1是由卷积层、批处理范数、LeakReLU激活函数组成。Encoder1将输入数据X转换成潜在表示,是Decoder用来重构输入数据的样本。Decoder是由卷积转置层、LeakReLU激活函数和批处理范数组成。第二个编码器Encoder2的网络结构与Encoder1相同,但参数不同,输出在数据维度上与相同。生成器不仅保证输入样本的特性,还保证在空间的模式可以同时学习。生成器的损失函数是通过式(1)三种损失函数之和来指示生成器:
L=ωfLfaLabLb (1)
式(1)中,Lf是差异损失,通过生成的样本输入判别器,根据判别器的输出来计算;La是表观损失,Lb是潜在损失,以最小化真实样本的潜在表示和生成样本的编码瓶颈特征之间的距离;ωf、ωa和ωb为超参数。
采用式(1)来指示生成器。
判别器的损失函数是通过式(2)来指示判别器:
Figure BDA0003363889680000091
式(2)中PG(x)表示生成数据分布,Pdata(x)表示真实数据分布,
Figure BDA0003363889680000092
Figure BDA0003363889680000093
代表两个数据分布的期望值;fw表示判别器,α表示正则项,
Figure BDA0003363889680000094
表示梯度惩罚项,
Figure BDA0003363889680000095
表示整个样本空间,其分布可由以下步骤得到:
①随机选取一个真实样本xi、一个生成样本
Figure BDA0003363889680000096
一个[0,1]随机数ε。
②得到插值样本
Figure BDA0003363889680000097
由式(3)表示:
Figure BDA0003363889680000098
③多个插值样本构成的分布,记作
Figure BDA0003363889680000099
图2展示了生成对抗网络模型图。
步骤3:将源数据集S1、源数据集S2和合成数据集T进行整合形成最终的整合数据集Q,并将其划分为训练集M和测试集N。此处的整合:将三个数据集合并。划分:按照0.33的比例随机选取整合后的数据集中的数据得到-训练集、测试集。
步骤4:用训练集M构建并训练根因分类器,对测试集N进行预测分类,根因分类器输出测试集N中可能的故障根因。调用分类器API进行训练,参照图3的故障根因定位系统结构图。图3中Original Dataset表示原始数据集,Generated Dataset表示生成的数据集,Generative Adversarial Nets model为生成对抗网络模型,Merge为合并操作,SVM为支持向量机模型,RF为随机森林模型,DT为决策树模型,Adaboost和Catboost为集成学习模型,Output Label为输出的标签。
步骤5:利用根因分类器的输出对测试集N中所有实例进行标记,得到标记结果c,所述标记结果c的标记值为0时,表示实例非故障根因,标记值为1时,表示实例为故障根因。
步骤5中采用式(4)计算得到标记结果c:
Figure BDA0003363889680000101
式(4)中,
Figure BDA0003363889680000102
为样本k的第i个特征,D为所有可用于模型训练的数据集,Dk为D中的子集,yj为样本j的特征值,a为参数,p为先验值。
步骤6:根据标记结果c,输出故障根因。
本实施例的一种面向网络智能运维系统的故障根因定位方法的定位系统,包括:
数据集划分模块,用于对从不平衡数据集中筛选出少类样本所形成的源数据集S1和多类样本所形成的源数据集S2。
生成对抗网络模型模块,用于对源数据集S1进行数据增强,以此生成高质量的合成数据,作为合成数据集T。
生成器:用于生成合成数据,以输入给判别器进行判别。
判别器:用于判别是原始数据还是合成数据,并计算二者之间的损失。
根因分类器,用于对测试集N进行预测,输出测试集N中每个实例故障根因。
标记模块,用于对测试集N中所有实例进行标记,得到标记结果。
显示模块,用于根据标记结果,定位并显示网络中的故障根因。
生成合成数据T并与源数据集S1和源数据集S2合并构成整合数据集Q。采用整合数据集Q构建根因分类器。
以上所述仅为本发明的较佳实施方式,本发明的保护范围并不以上述实施方式为限,但凡本领域普通技术人员根据本发明所揭示内容所作的等效修饰或变化,皆应纳入权利要求书中记载的保护范围内。

Claims (6)

1.一种面向网络智能运维系统的故障根因定位方法,其特征在于:包括以下步骤:
步骤1,将已经过标记的不平衡故障根因数据进行数据的划分,从中筛选出类别为少类的样本数据,即标签为1,将其作为源数据集S1,另一类样本,即标签为0,将其作为源数据集S2;
步骤2,采用生成对抗网络模型,首先利用生成器对源数据集S1进行数据的生成,再利用判别器对生成的数据进行损失计算,得到合成数据,将其作为合成数据集T;
步骤3,采用源数据集S1、源数据集S2和合成数据集T进行整合形成最终的整合数据集Q,并将其划分为训练集M和测试集N;
步骤4,用训练集M构建并训练根因分类器,对测试集N进行预测,根因分类器输出测试集N中可能的故障根因;
步骤5,利用根因分类器的输出对测试集N中所有实例进行标记,得到标记结果c,所述标记结果c的标记值为0时,表示实例非故障根因,标记值为1时,表示实例为故障根因;
步骤6:根据标记结果c,输出故障根因。
2.根据权利要求1所述的一种面向网络智能运维系统的故障根因定位方法,其特征在于:所述步骤2中的生成器采用编码器-解码器-编码器子网模型,其中两个编码器分别学习获取输入样本表示和生成样本表示,解码器尝试重构输入数据;将噪音数据X馈入第一个编码器Encoder1,Encoder1是由卷积层、批处理范数、LeakReLU激活函数组成;Encoder1将输入数据X转换成潜在表示,是Decoder用来重构输入数据的样本;Decoder是由卷积转置层、LeakReLU激活函数和批处理范数组成;第二个编码器Encoder2的网络结构与Encoder1相同,但参数不同,输出在数据维度上与相同;生成器的损失函数是通过式(1)三种损失函数之和来指示生成器:
L=ωfLfaLabLb (1)
式(1)中,Lf是差异损失,通过生成的样本输入判别器,根据判别器的输出来计算;La是表观损失,Lb是潜在损失,以最小化真实样本的潜在表示和生成样本的编码瓶颈特征之间的距离;ωf、ωa和ωb为超参数;
采用式(1)来指示生成器;
判别器的损失函数是通过式(2)来指示判别器:
Figure FDA0003363889670000021
式(2)中PG(x)表示生成数据分布,Pdata(x)表示真实数据分布,
Figure FDA0003363889670000022
Figure FDA0003363889670000023
代表两个数据分布的期望值;fw表示判别器,α表示正则项,
Figure FDA0003363889670000024
表示梯度惩罚项,
Figure FDA0003363889670000025
表示整个样本空间,其分布可由以下步骤得到:
随机选取一个真实样本xi、一个生成样本
Figure FDA0003363889670000026
一个[0,1]随机数ε;
得到插值样本
Figure FDA0003363889670000027
由式(3)表示:
Figure FDA0003363889670000028
多个插值样本构成的分布,记作
Figure FDA0003363889670000029
3.根据权利要求1所述的一种面向网络智能运维系统的故障根因定位方法,其特征在于:所述步骤5中采用式(4)计算得到标记结果c:
Figure FDA0003363889670000031
式(4)中,
Figure FDA0003363889670000032
为样本k的第i个特征,D为所有可用于模型训练的数据集,Dk为D中的子集,yj为样本j的特征值,a为参数,p为先验值。
4.基于权利要求1至3任意一项所述的一种面向网络智能运维系统的故障根因定位系统,其特征在于:包括:
数据集划分模块,用于对从不平衡数据集中筛选出少类样本所形成的源数据集S1和多类样本所形成的源数据集S2;
生成对抗网络模型模块,用于对源数据集S1进行数据增强,以此生成高质量的合成数据,作为合成数据集T;
生成器:用于生成合成数据,以输入给判别器进行判别;
判别器:用于判别是原始数据还是合成数据,并计算二者之间的损失;
根因分类器,用于对测试集N进行预测,输出测试集N中每个实例故障根因;
标记模块,用于对测试集N中所有实例进行标记,得到标记结果;
显示模块,用于根据标记结果,定位并显示网络中的故障根因。
5.根据权利要求4所述的一种面向网络智能运维系统的故障根因定位系统,其特征在于:生成对抗网络模型模块中,生成合成数据T并与源数据集S1和源数据集S2合并构成整合数据集Q。
6.根据权利要求5所述的一种面向网络智能运维系统的故障根因定位系统,其特征在于:采用整合数据集Q构建根因分类器。
CN202111375636.0A 2021-11-19 2021-11-19 一种面向网络智能运维系统的故障根因定位方法及其系统 Active CN114124676B (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111375636.0A CN114124676B (zh) 2021-11-19 2021-11-19 一种面向网络智能运维系统的故障根因定位方法及其系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111375636.0A CN114124676B (zh) 2021-11-19 2021-11-19 一种面向网络智能运维系统的故障根因定位方法及其系统

Publications (2)

Publication Number Publication Date
CN114124676A true CN114124676A (zh) 2022-03-01
CN114124676B CN114124676B (zh) 2024-04-02

Family

ID=80397952

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111375636.0A Active CN114124676B (zh) 2021-11-19 2021-11-19 一种面向网络智能运维系统的故障根因定位方法及其系统

Country Status (1)

Country Link
CN (1) CN114124676B (zh)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111190756A (zh) * 2019-11-18 2020-05-22 中山大学 一种基于调用链数据的根因定位算法
CN112003718A (zh) * 2020-09-25 2020-11-27 南京邮电大学 一种基于深度学习的网络告警定位方法
CN112039687A (zh) * 2020-07-14 2020-12-04 南京邮电大学 一种面向小样本特征的基于改进生成对抗网络的故障诊断方法
US20200387785A1 (en) * 2019-06-05 2020-12-10 Wuhan University Power equipment fault detecting and positioning method of artificial intelligence inference fusion
US20210028973A1 (en) * 2019-07-26 2021-01-28 Ciena Corporation Identifying and locating a root cause of issues in a network having a known topology
CN112308038A (zh) * 2020-11-25 2021-02-02 哈尔滨工业大学 基于课堂式生成对抗网络模型的机械设备故障信号识别方法
US20210197335A1 (en) * 2019-12-26 2021-07-01 Dalian University Of Technology Data Augmentation Method Based On Generative Adversarial Networks In Tool Condition Monitoring

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200387785A1 (en) * 2019-06-05 2020-12-10 Wuhan University Power equipment fault detecting and positioning method of artificial intelligence inference fusion
US20210028973A1 (en) * 2019-07-26 2021-01-28 Ciena Corporation Identifying and locating a root cause of issues in a network having a known topology
CN111190756A (zh) * 2019-11-18 2020-05-22 中山大学 一种基于调用链数据的根因定位算法
US20210197335A1 (en) * 2019-12-26 2021-07-01 Dalian University Of Technology Data Augmentation Method Based On Generative Adversarial Networks In Tool Condition Monitoring
CN112039687A (zh) * 2020-07-14 2020-12-04 南京邮电大学 一种面向小样本特征的基于改进生成对抗网络的故障诊断方法
CN112003718A (zh) * 2020-09-25 2020-11-27 南京邮电大学 一种基于深度学习的网络告警定位方法
CN112308038A (zh) * 2020-11-25 2021-02-02 哈尔滨工业大学 基于课堂式生成对抗网络模型的机械设备故障信号识别方法

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
刘军;李鑫;王颖;赵永利;王菲;: "基于深度神经网络的光网络故障定位技术研究", 激光杂志, no. 07, 25 July 2020 (2020-07-25) *
闫?颖;何云瑞;陈亮;王宁;李扬;郑思远;: "基于CMDB的信息系统故障根因定位技术的研究", 通信电源技术, no. 03 *
陈文兵;管正雄;陈允杰;: "基于条件生成式对抗网络的数据增强方法", 计算机应用, no. 11, 10 November 2018 (2018-11-10) *

Also Published As

Publication number Publication date
CN114124676B (zh) 2024-04-02

Similar Documents

Publication Publication Date Title
CN113887616B (zh) 一种epg连接数的实时异常检测方法
CN112084237A (zh) 一种基于机器学习和大数据分析的电力系统异常预测方法
Du et al. GAN-based anomaly detection for multivariate time series using polluted training set
Dou et al. Pc 2 a: predicting collective contextual anomalies via lstm with deep generative model
CN115099335A (zh) 多源异构数据的异常辨识和特征筛选方法、系统
Cheng et al. Online power system event detection via bidirectional generative adversarial networks
Mehmood et al. A novel approach to improve software defect prediction accuracy using machine learning
Li et al. Mining static code metrics for a robust prediction of software defect-proneness
CN118037047A (zh) 基于ai的矿山安全监控系统
CN113485863A (zh) 基于改进生成对抗网络生成异构不平衡故障样本的方法
Zhang et al. Automatic Traffic Anomaly Detection on the Road Network with Spatial‐Temporal Graph Neural Network Representation Learning
CN106846170B (zh) 一种发电机组跳闸监测方法及其监测装置
Jiao et al. Reduced-space multistream classification based on multiobjective evolutionary optimization
CN118230069A (zh) 一种基于数据分析的污水处理故障诊断方法及系统
Xu et al. Concept drift and covariate shift detection ensemble with lagged labels
Xie et al. Machine learning control charts for monitoring serially correlated data
Raju et al. Development of anomaly-based intrusion detection scheme using deep learning in data network
Ma et al. Research on multi-granularity imbalanced knowledge condition monitoring for mechanical equipment based on hierarchical ELM in multi-entropy space
CN114124676A (zh) 一种面向网络智能运维系统的故障根因定位方法及其系统
CN115426194A (zh) 数据处理方法及装置、存储介质及电子设备
Ahmed et al. O-LoMST: An online anomaly detection approach and its application in a hydropower generation plant
Abadeh et al. Computer intrusion detection using an iterative fuzzy rule learning approach
Bordeau-Aubert et al. Classification of Anomalies in Telecommunication Network KPI Time Series
Sheelavathy et al. Detection IoT attacks using Lasso regression algorithm with ensemble classifier
Paes Leao et al. Unleashing the Power of Industrial Big Data through Scalable Manual Labeling

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20220301

Assignee: Nanjing Benli Information Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980016890

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20240927

Application publication date: 20220301

Assignee: Nanjing Eryuefei Network Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980016831

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20240927

EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20220301

Assignee: Nanjing Zhujin Intelligent Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980017765

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241010

Application publication date: 20220301

Assignee: Nanjing Shangyao Electronic Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980017764

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241010

Application publication date: 20220301

Assignee: Nanjing Qida Network Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980017763

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241010

Application publication date: 20220301

Assignee: Nanjing Donglai Information Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980017666

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241009

Application publication date: 20220301

Assignee: Nanjing Zijin Information Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980017766

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241010

EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20220301

Assignee: Nanjing Yuanshen Intelligent Technology R&D Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018301

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Yuze Robot Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018300

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Zhongyang Information Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018299

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Fangtai Intelligent Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018298

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Gaoxi Information Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018297

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Fuliang Network Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018296

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Yixun Intelligent Equipment Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018292

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Yihe Information Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018291

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Xingzhuo Intelligent Equipment Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018289

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Tichi Information Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018288

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Jindong Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018286

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Jinsheng Artificial Intelligence Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018283

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Jingda Environmental Protection Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018281

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Hancong Robot Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018278

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Jiangsu Huida Information Technology Industry Development Research Institute Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018270

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Extreme New Materials Research Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018268

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Youqi Intelligent Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018261

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Haohang Intelligent Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018249

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Pengjia Robot Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018246

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Nuoyan Intelligent Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018241

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012

Application publication date: 20220301

Assignee: Nanjing Junshang Network Technology Co.,Ltd.

Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS

Contract record no.: X2024980018234

Denomination of invention: A Fault Root Cause Localization Method and System for Network Intelligent Operation and Maintenance System

Granted publication date: 20240402

License type: Common License

Record date: 20241012