首页> 外文OA文献 >Methods for Self-Healing based on traces and unsupervised learning in Self-Organizing Networks
【2h】

Methods for Self-Healing based on traces and unsupervised learning in Self-Organizing Networks

机译:自组织网络中基于痕迹和无监督学习的自我修复方法

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

With the advent of Long-Term Evolution (LTE) networks and the spread of a highly varied range ofservices, mobile operators are increasingly aware of the need to strengthen their maintenance andoperational tasks in order to ensure a quality and positive user experience. Furthermore, the co-existence of multiple Radio Access Technologies (RAT), the increase in the traffic demand and the needto provide a great variety of services are steering the cellular network toward a new scenario wheremanagement tasks are becoming increasingly complex. As a result, mobile operators are focusing theirefforts to deal with the maintenance of their networks without increasing either operationalexpenditures (OPEX) or capital expenditures (CAPEX). In this context, it is becoming necessary toeffectively automate the management tasks through the concept of the Self-Organizing Networks (SON).In particular, SON functions cover three different areas: Self-Configuration, Self-Optimization and Self-Healing. Self-Configuration automates the deployment of new network elements and their parameterconfiguration. Self-Optimization is in charge of modifying the configuration of the parameters in order toenhance user experience. Finally, Self-Healing aims reduce the impact that failures and servicesdegradation have on the end-user. To that end, Self-Healing (SH) systems monitor the network elementsthrough several alarms, measurements and indicators in order to detect outage and degraded cells,then, diagnose the cause of their problem and, finally, execute the compensation or recovery actions.Even though mobile networks are become more prone to failures due to their huge increase incomplexity, the automation of the troubleshooting tasks through the SH functionality has not been fullyrealized. Traditionally, both the research and the development of SON networks have been related toSelf-Configuration and Self-Optimization. This has been mainly due to the challenges that need to befaced when SH systems are studied and implemented. This is especially relevant in the case of faultdiagnosis. However, mobile operators are paying increasingly more attention to self-healing systems,which entails creating options to face those challenges that allow the development of SH functions.On the one hand, currently, the diagnosis continues to be manually done since it requires considerablehard-earned experience in order to be able to effectively identify the fault cause. In particular,troubleshooting experts thoroughly analyze the performance of the degraded network elements bymeans of measurements and indicators in order to identify the cause of the detected anomalies andsymptoms. Therefore, automating the diagnosis tasks means knowing what specific performanceindicators have to be analyzed and how to map the identified symptoms with the associate fault cause.This knowledge is acquired over time and it is characterized by being operator-specific based on theirpolicies and network features. Furthermore, troubleshooting experts typically solve the failures in anetwork without either documenting the troubleshooting process or recording the analyzed indicatorsalong with the label of the identified fault cause. In addition, because there is no specific regulation ondocumentation, the few documented faults are neither properly defined nor described in a standardway (e.g. the same fault cause may be appointed with different labels), making it even more difficult toautomate the extraction of the expert knowledge. As a result, this a lack of documentation and lack ofhistorical reported faults makes automation of diagnosis process more challenging.On the other hand, when the exact root cause cannot be remotely identified through the statisticalinformation gathered at cell level, drive test are scheduled for further information. These drive tests aimto monitor mobile network performance by using vehicles to personally measure the radio interfacequality along a predefined route. In particular, the troubleshooting experts use specialized testequipment in order to manually collect user-level measurements. Consequently, drive test entail a heftyexpense for mobile operators, since it involves considerable investment in time and costly resources(such as personal, vehicles and complex test equipment). In this context, the Third GenerationPartnership Project (3GPP) has standardized the automatic collection of field measurements (e.g.signaling messages, radio measurements and location information) through the mobile traces featuresand its extended functionality, the Minimization of Drive Tests (MDT). In particular, those features allowto automatically monitor the network performance in detail, reaching areas that cannot be covered bydrive testing (e.g. indoor or private zones). Thus, mobile traces are regarded as an important enabler forSON since they avoid operators to rely on those expensive drive tests while, at the same time, providegreater details than the traditional cell-level indicators. As a result, enhancing the SH functionalitiesthrough the mobile traces increases the potential cost savings and the granularity of the analysis. Hence,in this thesis, several solutions are proposed to overcome the limitations that prevent the developmentof SH with special emphasis on the diagnosis phase. To that end, the lack of historical labeled databaseshas been addressed in two main ways. First, unsupervised techniques have been used to automaticallydesign diagnosis system from real data without requiring either documentation or historical reportsabout fault cases. Second, a group of significant faults have been modeled and implemented in adynamic system level simulator in order to generate an artificial labeled database, which is extremelyimportant in evaluating and comparing the proposed solutions with the state-of- the-art algorithm. Then,the diagnosis of those faults that cannot be identified through the statistical performance indicatorsgathered at cell level is automated by the analysis of the mobile traces avoiding the costly drive test. Inparticular, in this thesis, the mobile traces have been used to automatically identify the cause of eachunexpected user disconnection, to geo-localize RF problems that affect the cell performance and toidentify the impact of a fault depending on the availability of legacy systems (e.g. Third Generation, 3G).Finally, the proposed techniques have been validated using real and simulated LTE data by analyzing itsperformance and comparing it with reference mechanisms.
机译:随着长期演进(LTE)网络的出现以及各种各样服务的普及,移动运营商越来越意识到需要加强维护和运营任务以确保高质量和积极的用户体验。此外,多种无线电接入技术(RAT)的共存,业务需求的增长以及提供多种服务的需求正在使蜂窝网络朝着管理任务变得越来越复杂的新场景发展。结果,移动运营商将精力集中在处理其网络维护上,而不增加运营支出(OPEX)或资本支出(CAPEX)。在这种情况下,有必要通过自组织网络(SON)的概念有效地实现管理任务的自动化。特别是SON功能涵盖三个不同的领域:自我配置,自我优化和自我修复。自我配置可自动部署新网络元素及其参数。自我优化负责修改参数的配置,以增强用户体验。最后,自我修复的目标是减少故障和服务降级对最终用户的影响。为此,自愈(SH)系统通过多个警报,测量值和指示器监视网络元素,以检测故障和降级的电池,然后诊断出问题的原因,最后执行补偿或恢复操作。尽管移动网络由于其复杂性的极大增加而变得更容易出现故障,但是通过SH功能实现故障排除任务的自动化尚未完全实现。传统上,SON网络的研究和开发都与自配置和自优化有关。这主要是由于研究和实施SH系统时需要面对的挑战。这在故障诊断的情况下尤其重要。但是,移动运营商越来越重视自我修复系统,这需要创建解决方案以应对那些允许开发SH功能的挑战。一方面,由于需要相当大的困难,因此目前诊断仍需手动进行积累经验,以便能够有效地识别故障原因。尤其是,故障排除专家会通过测量和指标的手段来全面分析降级的网络元素的性能,以便确定检测到的异常和症状的原因。因此,使诊断任务自动化意味着知道必须分析哪些特定的性能指标以及如何将所识别的症状与相关的故障原因进行映射。随着时间的流逝,该知识将被获取,并且其特征是基于其策略和网络特征的特定于运营商的特征。此外,故障排除专家通常可以解决网络中的故障,而无需记录故障排除过程或记录已分析的指标以及已识别故障原因的标签。另外,由于没有关于文档的特殊规定,很少有记录的故障既没有正确定义也没有以标准方式描述(例如,相同的故障原因可能用不同的标签指定),这使得自动提取专家知识变得更加困难。 。结果,缺乏文档和历史错误的记录使诊断过程的自动化更具挑战性。另一方面,当无法通过在单元级别收集的统计信息来远程确定确切的根本原因时,将安排进行驾驶测试信息。这些路测旨在通过使用车辆沿着预定路线亲自测量无线电接口质量来监视移动网络性能。特别是,故障排除专家使用专门的测试设备来手动收集用户级别的测量值。因此,路测会给移动运营商带来沉重的成本,因为它涉及大量的时间和昂贵的资源(例如个人,车辆和复杂的测试设备)投资。在这种情况下,第三代合作伙伴计划(3GPP)通过移动跟踪功能及其扩展功能,最小化路测(MDT),标准化了现场测量(例如信号消息,无线电测量和位置信息)的自动收集。特别是,这些功能允许自动详细监视网络性能,以达到路测无法覆盖的区域(例如室内或私有区域)。因此,移动跟踪被视为SON的重要推动因素,因为它们避免了操作员依赖那些昂贵的路测,而同时,提供比传统单元格级别指标更大的详细信息。结果,通过移动迹线增强SH功能会增加潜在的成本节省和分析的粒度。因此,在本文中,提出了几种解决方案来克服阻碍SH发展的局限性,特别是在诊断阶段。为此,可以通过两种主要方法来解决缺乏历史标签数据库的问题。首先,无监督技术已用于根据实际数据自动设计诊断系统,而无需有关故障案例的文档或历史报告。其次,已经在动态系统级模拟器中对一组重大故障进行了建模和实现,以生成人工标记的数据库,这在评估和比较所提出的解决方案与最新算法方面非常重要。然后,通过对移动迹线进行分析,可以自动诊断那些无法通过在单元级别聚集的统计性能指标来识别的故障,从而避免进行昂贵的路测。特别是,在本文中,移动跟踪已用于自动识别每个意外用户断开连接的原因,对影响电池性能的RF问题进行地理定位,并根据遗留系统的可用性确定故障的影响(例如,最后,通过分析其性能并将其与参考机制进行比较,使用真实和模拟的LTE数据对提出的技术进行了验证。

著录项

  • 作者

    Gómez Andrades Ana;

  • 作者单位
  • 年度 2016
  • 总页数
  • 原文格式 PDF
  • 正文语种 spa
  • 中图分类

相似文献

  • 外文文献
  • 中文文献
  • 专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号