icon_CloudMgmt icon_DollarSign icon_Globe icon_ITAuto icon_ITOps icon_ITSMgmt icon_Mainframe icon_MyIT icon_Ribbon icon_Star icon_User icon_Users icon_VideoPlay icon_Workload icon_caution icon_close s-chevronLeft s-chevronRight s-chevronThinRight s-chevronThinRight s-chevronThinLeft s-chevronThinLeft s-trophy s-chevronDown

AIOps 利用大数据、机器学习和分析来帮助 ITOps 更快地预测、查找和修复问题。


数字业务转型迫使 IT 组织重新考虑如何确保基础设施和应用程序性能。多重云基础设施带来的速度、规模和复杂性以及数字化给基于规则的传统性能监控和管理带来了压力。AIOps 应用机器学习和高级分析技术来确定监控、服务台和自动化数据中的模式,这些模式非常庞大,超出了人工理解的范畴。采用 AIOps 让 IT 运营团队能够:

  • 减少事件噪音并确定最关键业务问题的优先级,以提高性能
  • 支持应用程序体系结构更改和 DevOps 采用的速度
  • 主动发现问题并快速查明根本原因以减少 MTTR
  • 模拟和预测工作负载容量需求,以优化资源使用和成本

“AIOps 平台将大数据和机器学习功能相结合,通过以可扩展方式接收和分析 IT 生成的且数量、种类和速度都日益增加的数据,来支持所有主要的 IT 运营职能。”

来源:Gartner AIOps 平台市场指南,2018 年 11 月 12 日

AIOps 方法的关键要素

实施 AIOps 方法不仅仅是获得更好的现有数据分析。为获得持续洞察的机器学习系统奠定基础需要:

BMC is a trusted leader in AIOps

BMC solutions deploy machine learning and advanced analytics as part of a holistic monitoring, event management, capacity and automation solution to deliver AIOps use cases that help IT Ops run at the speed that digital business demands.

  • Reduce event noise by 90%
  • Predictively alert to reduce incidents by 40%
  • Reduce time to identify root cause by 60%
  • Automate event remediation to reduce MTTR by 75%
Open Data Access

Open data access

Observability teams must be able to consume huge volumes of data and events across multiple technologies and systems of record as the basis for a successful AIOps strategy. Key requirements include:

  • Monitoring distributed applications across on-premises, cloud and container environments
  • Achieving a unified data view across different layers of the app stack
  • Data agnostic monitoring, including taking in data from other monitoring tools

Machine learning

IT analytics is ultimately about pattern matching. Machine learning applies the computational power and speed of machines to the discovery and correlation of patterns in IT data. It does this more and faster than human agents and dynamically changes the algorithms used by analytics based on changes in the data.

  • Behavorial learning of normal conditions
  • Dynamic baselines extend beyond static thresholds
  • Anomaly detection based on learned patterns
AIOps and ITSM automation

AIOps and ITSM automation

Tangible AIOps value comes from using the rich insights delivered by machine learning and analytics to power automation and break down the silos between ITOM and ITSM to drive maximum business value. Valuable AIOps automation use cases include:

AIOps 轻松入门