Machine Learning für Event Management
1 like566 views
Erleichtern des Service-Betriebs und Steigern der Event-Zuverlässigkeit mit Machine Learning und Event Analytics. Ihr Rechenzentrum erzeugt eine Unmenge von Events. Diese reichen von harmlosen Festplatten-Warnmeldungen bis hin zu kritischen Netzwerkproblemen und sogar Ausfällen auf Serviceebene. Wie wissen Sie bei so vielen Events und False Positives, welche Events wichtig sind und welche Sie getrost ignorieren können? Ihre aktuellen, regelbasierten Tools sind da keine Hilfe: Sie sind unflexibel, können das Event-Volumen der heutigen, veränderlichen Infrastrukturen nicht verarbeiten und liefern keine aussagekräftigen Benachrichtigungen, die Ihnen die Priorisierung der Probleme nach Wichtigkeit erleichtern. Nehmen Sie am Webinar teil um zu erfahren, wie sich Splunk IT Service Intelligence das Potenzial von Machine Learning zunutze macht, um in einer integrierten Lösung belastbare und nach menschlichem Maßstab zu bewältigende Benachrichtigungen mit Servicekontext zu liefern, dank derer sich IT-Teams schnell und einfach auf die Problembehebung konzentrieren können. Erfahren Sie, wie Sie Machine Learning schnell für folgende Zwecke einsetzen können: - Anomales Verhalten entdecken, um Events aufzuspüren, bevor sie zu kritischen Vorfällen werden - Erstellung manueller Regeln vermeiden und Schwellenwerte dynamisch anpassen - Daten automatisch korrelieren, um höchst qualifizierte Ergebnisse zu erzeugen, die schnell Maßnahmen ermöglichen - Untersuchung der wichtigsten Vorfälle durch Servicekontext priorisieren und beschleunigen
Ad
More Related Content
What's hot (20)
Similar to Machine Learning für Event Management (20)
Ad
More from Splunk (20)
Ad
Recently uploaded (20)
Machine Learning für Event Management
- 1. © 2017 SPLUNK INC.© 2017 SPLUNK INC.© 2017 SPLUNK INC.© 2017 SPLUNK INC. Rage with the machine, not against it @splunk Machine Learning für Event Management
- 2. © 2017 SPLUNK INC.© 2017 SPLUNK INC. During the course of this presentation, we may make forward-looking statements regarding future events or the expected performance of the company. We caution you that such statements reflect our current expectations and estimates based on factors currently known to us and that actual events or results could differ materially. For important factors that may cause actual results to differ from those contained in our forward-looking statements, please review our filings with the SEC. The forward-looking statements made in this presentation are being made as of the time and date of its live presentation. If reviewed after its live presentation, this presentation may not contain current or accurate information. We do not assume any obligation to update any forward looking statements we may make. In addition, any information about our roadmap outlines our general product direction and is subject to change at any time without notice. It is for informational purposes only and shall not be incorporated into any contract or other commitment. Splunk undertakes no obligation either to develop the features or functionality described or to include any such feature or functionality in a future release. Splunk, Splunk>, Listen to Your Data, The Engine for Machine Data, Splunk Cloud, Splunk Light and SPL are trademarks and registered trademarks of Splunk Inc. in the United States and other countries. All other brand names, product names, or trademarks belong to their respective owners. © 2017 Splunk Inc. All rights reserved. Forward-Looking Statements
- 3. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Who We Are Juergen Magiera ITOA Lead, EMEA Hans-Henning Gehrts SE / ITOA SME @tiras_de
- 4. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Ask questions throughout in the Q&A window
- 5. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Four things you will learn today What ML is critical for today’s IT Why Google Images has inspired us to manage IT events better How Splunk can help you with a negative MTTD How Splunk is helping the World Bank solve world hunger 1 2 3 4
- 6. © 2017 SPLUNK INC.© 2017 SPLUNK INC. We’re living in a digital revolution
- 7. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Companies must meet high customer expectations to survive I don’t want to deal with delays I expect you to know who I am when I call I expect to be able to track my baggage in real-time I expect the lowest price I expect you to respond quickly to my issues I expect you to help me make my connection I expect a perfect safety record
- 8. © 2017 SPLUNK INC.© 2017 SPLUNK INC.
- 9. © 2017 SPLUNK INC.© 2017 SPLUNK INC. No one is too big to fail
- 10. © 2017 SPLUNK INC.© 2017 SPLUNK INC. This requires IT to focus on • Aligning with the business • Improving customer experience • Accelerating time to value • Develop new digital services
- 11. © 2017 SPLUNK INC.© 2017 SPLUNK INC. But really, how much time do we spend doing this? Searching lots of data in silos Creating static rules Monitoring Troubleshooting Root Cause Analysis Capacity Planning War Rooms Forecasting ….
- 12. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Some tasks in IT are beyond human scale
- 13. © 2017 SPLUNK INC.© 2017 SPLUNK INC. So many screens
- 14. © 2017 SPLUNK INC.© 2017 SPLUNK INC. How do you manage your events & alerts today? • Increasing number to manage • Different formats and fields • Difficult to parse • Required to aggregate • Very little context
- 15. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Common problems with managing events Event overload | Silos of “monitoring” | Loss of data fidelity | Manual events interpretation Custom integrations | Rules management overhead | Context and impact blindness Bloated Products and Features Complex Integrations Alerts Storm Cumbersome Rules Management Duplicate Incidents | Repeat Incidents
- 16. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Machine Skills • Creative • Design • Empathy • Intuition • Sales • Marketing • Business Acumen • Analyzing high-velocity data • Analyzing big data sets • Complex data sets • Predicting future values • Detect Anomalies • Complex patterns Human Skills
- 17. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Rethink and Improve How IT Operates Traditional IT ▶ Structured data ▶ Brittle tools and integrations ▶ Obsession with “faults” and “traps” ▶ Focus on components parts ▶ Search oriented Data Driven IT 0101101 0010101 ▶ Structured and unstructured data ▶ Robust data integrations ▶ Real-time insights from big data ▶ Focus on the whole service ▶ Machine learning-driven analytics Using Artificial Intelligence for IT Operations
- 18. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Poll 18 What’s your biggest challenge with the alerts your receive from your different monitoring solutions I don’t bother looking at them, they go into my spam Too many to manage, too many false positives Alert storms makes it difficult to see what’s wrong I spend too much time configuring rules
- 19. © 2017 SPLUNK INC.© 2017 SPLUNK INC. How do we sort your images?
- 20. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Do I need to be a data scientist for this? Do I need to understand what algorithms are being used?
- 21. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Intelligently grouped through machine learning. No programming or configuration involved
- 22. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Manage the Incident, Not the Event Collect ALL data De-spam: Separate valuable signal from noise Add context: Prioritize resolution to ensure service availability Shared insights Collaborative response Data-enabled IT Intelligent operations SALES SSO CLAIMS
- 23. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Machine Learning Made Mainstream Adaptive Thresholds Anomaly Detection Event Correlation Manage and maintain KPI thresholds by dynamically adapting to changing operational patterns Catch issues that thresholds can’t—baseline normal operations and alert on anomalous conditions Reduce event clutter, false positives and rules maintenance by auto-grouping related events
- 24. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Build on top of our platform Network InfrastructureLayer Packet, Payload, Traffic, Utilization, Perf Storage Utilization, Capacity, Performance Server Performance, Usage, Dependency ApplicationLayer User Experience Usage, Response Time, Failed Interactions Byte Code Instrumentation Usage, Experience, Performance, Quality Business Performance Corporate Data, Intake, Output, Throughput Splunk Approach: ▶ Single repository for ALL data ▶ Data in original raw format ▶ Machine learning ▶ Simplified architecture ▶ Fewer resources to manage ▶ Collaborative approach MACHINE DATA
- 25. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Splunk ITSI in Action (Demo)
- 26. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Splunk ITSI for Event Analytics Simplify Your Operations With Artificial Intelligence and Service Context Find and fix the most important issues Transform IT operations with machine learning Get a full view of your IT environment Service Context Artificial Intelligence Scalable Platform Reduce time-to-resolution on business-critical services Enable IT with intelligence for data-driven decisions Share customized insights across the enterprise to enable business-centric IT Contextualize and prioritize Separate valuable signal in noise Respond collaboratively and simplify operations 1001001 0100010 0101001 1001101 0110010111000110 1101011101010110 0010011101011000
- 27. © 2017 SPLUNK INC.© 2017 SPLUNK INC.
- 28. Thanks to the integrated machine learning in Splunk ITSI, we now have a reduced number of events to process and the streamlined event analytics framework allows us to process events eight minutes more quickly Laurent Amouroux, Technical Director Econocom Infrastructure Management Services 15% increased SLA Performance 60% reduction In number of events 10x reduction in number of system performance events through machine learning
- 29. © 2017 SPLUNK INC.© 2017 SPLUNK INC. What to do next?
- 30. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Try it for yourself - free Sandbox http://splunk.com/itsi
- 31. © 2017 SPLUNK INC.© 2017 SPLUNK INC. #Splunk4Rookies In major cities in Europe | Afterworks | 2.5 hours | Free | 100% hands-on | Beer & pizza #Splunk4Ninjas ITSI
- 32. © 2017 SPLUNK INC.© 2017 SPLUNK INC. We’re Here to Help! Harness the creativity and domain knowledge of your organization to unlock the value of data and solve an important business service problem through a joint service intelligence workshop with key stakeholders Define methods for: • Increased business performance • Improved customer satisfaction • Continuous improvement • Proactive service monitoring What is it? • Collaborative workshop • Tightly linked with business value • Build a functioning example
- 33. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Poll Would you be interesting in a follow-up discussion with one of our experts or be interested in attending one of our Rookies/Ninjas Yes No
- 34. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Die nächsten Termine https://www.splunk.com/de_de/about-us/events.html
- 35. © 2017 SPLUNK INC.© 2017 SPLUNK INC. Please respond to our survey
- 36. © 2017 SPLUNK INC. Q&A