The Future of Broadband Access Network Architecture and Intelligent Operations

C. Yang, Guangzhi Li, Xiang Liu, Zonghuan Wu, Kaiyu Zhang
{"title":"The Future of Broadband Access Network Architecture and Intelligent Operations","authors":"C. Yang, Guangzhi Li, Xiang Liu, Zonghuan Wu, Kaiyu Zhang","doi":"10.1109/CyberC.2019.00060","DOIUrl":null,"url":null,"abstract":"This paper presents an overview of the evolution towards a broadband optical access network. Network operations transformation with emphasis on automated broadband service monitoring, fault detection, fault recovery, and fault prediction is also discussed. However, in order to support broadband access network evolution and to accelerate telco operations transformation, traditional network operations, administration and maintenance (OAM) methods will not be sufficient. Therefore, we describe our key research contributions regarding new approaches to support closed-loop broadband network OAM that will eliminate human touches and automate non-physical fault recovery for daily routine tasks. We have designed and implemented a network knowledge engine (NKE) centered software framework to enable data collection, correlation, and analysis for troubleshooting complex issues in the broadband access network. Our solutions will address the following network management domains, including (a) knowledge management, (b) surveillance management, (c) incident management, and (d) problem management. In this paper, we focus on auto proactive and predictive trouble management which can verify and confirm a passive device problem location by NKE. We will describe a step-by-step methodology to control data process flow, optical fiber path discovery management, and auto-detection of failed passive devices by using the following techniques: (a) big data analytics, (b) knowledge graph, (c) machine learning (ML), and (d) artificial intelligence (AI) prediction rule and learning policy involving the spatial-temporal algorithm. With combinations of these technique, our preliminary study indicates that the accuracy of auto fault detection is 93%, while the false positive rate is ~0.01%. As results, we demonstrated the promise of this novel technology framework in supporting transformation from expert’s domain knowledge into machine knowledge.","PeriodicalId":397938,"journal":{"name":"2019 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)","volume":"27 9","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CyberC.2019.00060","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

This paper presents an overview of the evolution towards a broadband optical access network. Network operations transformation with emphasis on automated broadband service monitoring, fault detection, fault recovery, and fault prediction is also discussed. However, in order to support broadband access network evolution and to accelerate telco operations transformation, traditional network operations, administration and maintenance (OAM) methods will not be sufficient. Therefore, we describe our key research contributions regarding new approaches to support closed-loop broadband network OAM that will eliminate human touches and automate non-physical fault recovery for daily routine tasks. We have designed and implemented a network knowledge engine (NKE) centered software framework to enable data collection, correlation, and analysis for troubleshooting complex issues in the broadband access network. Our solutions will address the following network management domains, including (a) knowledge management, (b) surveillance management, (c) incident management, and (d) problem management. In this paper, we focus on auto proactive and predictive trouble management which can verify and confirm a passive device problem location by NKE. We will describe a step-by-step methodology to control data process flow, optical fiber path discovery management, and auto-detection of failed passive devices by using the following techniques: (a) big data analytics, (b) knowledge graph, (c) machine learning (ML), and (d) artificial intelligence (AI) prediction rule and learning policy involving the spatial-temporal algorithm. With combinations of these technique, our preliminary study indicates that the accuracy of auto fault detection is 93%, while the false positive rate is ~0.01%. As results, we demonstrated the promise of this novel technology framework in supporting transformation from expert’s domain knowledge into machine knowledge.
宽带接入网架构与智能化运营的未来
本文介绍了宽带光接入网的发展概况。讨论了以自动化宽带业务监控、故障检测、故障恢复和故障预测为重点的网络运营转型。然而,为了支持宽带接入网的演进和加速电信运营转型,传统的网络运营、管理和维护(OAM)方法将无法满足需求。因此,我们描述了我们在支持闭环宽带网络OAM的新方法方面的主要研究贡献,这些新方法将消除人类接触并自动执行日常任务的非物理故障恢复。我们设计并实现了一个以网络知识引擎(NKE)为中心的软件框架,使数据收集、关联和分析能够解决宽带接入网中的复杂问题。我们的解决方案将涉及以下网络管理领域,包括(a)知识管理,(b)监视管理,(c)事件管理和(d)问题管理。本文主要研究自动主动和预测性故障管理,利用NKE对无源设备的故障定位进行验证和确认。我们将描述一个循序渐进的方法,通过使用以下技术来控制数据处理流,光纤路径发现管理和故障无源器件的自动检测:(a)大数据分析,(b)知识图,(c)机器学习(ML)和(d)人工智能(AI)预测规则和涉及时空算法的学习策略。结合这些技术,我们的初步研究表明,自动故障检测的准确率为93%,而误报率为~0.01%。作为结果,我们证明了这种新技术框架在支持从专家领域知识到机器知识的转换方面的承诺。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书