Via Aiops Use Cases
Intelligent Service Operations with VIA AIOps
Enhance customer experience, lower cost, and improve operational efficiency with VIA AIOps
VIA AIOps enables a new service assurance operating model and a new way of working through automation powered by real-time analytics, artificial intelligence, and machine learning.
North American MSO Enables Intelligent Operations with Natural Language Processing and GenAI-Based ChatOps
LEADING MSO
Hundreds of Operations Staff
Accelerate Incident Response and Resolution
PROBLEM:
Siloed operations, communication through ticketing. observability and automation platforms not integrated with collaboration tools
IMPACT:
Miscommunication, disparate information and tools with resulting impacts to efficiency and productivity
SOLUTION:
Streamline communication by providing access to all relevant data through conversational ChatOps interactions. Integrate with VIA’s AlOps Automation framework to drive actions while minimizing impact to existing workflows and processes by integrating with existing collaboration tools
RESULTS:
Improved collaboration and cross-team alignment. Enhanced collaboration, audit trails created for all actions, and improved knowledge sharing
KPI:
Accelerated incident response and resolution
FOR INCIDENT MANAGEMENT
Breakdown Operational Silos and Improve Response and Resolution Time with VIA AIOps
- Eliminates miscommunication and resulting ping-pong issue movement from one fix team to another
- Integrates with existing communication tools
- Enables AIOps info access without need to onboard a new UI
- Reduces miscommunication & fosters transparency
- Find root cause and the right fix quickly accelerating both incident response and resolution time
Tier 1 MSO
Uses GenAI to Empower Likely Fix Recommendations
LEADING MSO
Hundreds of Operations Staff
Tier 1 MSO Uses GenAI to Empower
Likely Fix Recommendations
PROBLEM:
Costly manual analysis to determine the right fix; sometimes quick fixes implemented that hide instead of solve problems
IMPACT:
Unreasonable time to resolve issues
SOLUTION:
Leverage GenAI to determine the “likely fix” for incidents using GenAI models trained on incident tickets, war room chats, transcripts and knowledge bases
RESULTS:
Reduction in OPEX associated with costly manual analysis, improvement in network incident response, and reduction in downtime
KPI:
Reduced Mean Time to Resolve, Lowered OPEX
FOR INCIDENT MANAGEMENT
Automate incident management process and reduce cost with VIA AIOps
- GenAI recognizes patterns in data that may not be immediately apparent to humans
- Enables continuous leaning and codification of subject matter expertise
- GenAI quickly analyzes large datasets, provides recommendations in real-time
- Delivers end-to-end incident resolution process automation
- Reduces time and cost associated with root cause analysis and the determination of the right fix
Leading Network Operator uses VIA AIOps for Automated Incident Management
LEADING NETWORK OPERATOR
Hundreds of Operations Staff
Reduced Incidents by 65%
PROBLEM:
Detecting cause of degraded application performance in Kubernetes-based applications
IMPACT:
Application crashes and end user experience issues
SOLUTION:
VIA AIOps identifies memory leaks in Kubernetes-based applications in minutes or hours
RESULTS:
Change-related service impact is immediately detected, and truck rolls are avoided
KPI:
Improved application performance and user experience
FOR INCIDENT MANAGEMENT
Transform Fault Management with Process Automation Using VIA AIOps
- Monitor and analyze syslog, trap, and alarms events from physical and virtual hosts within and across technology layers and applications in real-time
- Enriches data through contextualization using machine-learned topologies and dimension discovery analysis
- Automatically generates baselines for every metric and dimension combination to detect faults more accurately
- Aggregates as appropriate multiple signals though process automation that may appear across service domains to a single incident
- Process automation powered by AI and machine learning defines probable root cause, symptoms and population impacted for rapid action and resolution
- Communicates bidirectionally with service management systems
An Over-the-Top Video Service Provider Improves Customer Experience with VIA AIOps
Video Service Provider
Over 30 Million Subscribers
Reduced Failure Rate by 28%
PROBLEM:
Over 140,000 failed application access attempts per day caused customer dissatisfaction
IMPACT:
Customer churn, call center overrun
SOLUTION:
Correlate app failures to network elements; root cause, auto-triage, proper incident assignment
RESULTS:
Improved application access performance, reduced call center interactions
KPI:
Removed 11M failures per year and ~250k customer support calls per year (equivalent to approximately ~20 full time staff and $2.3M / year)
FOR CUSTOMER EXPERIENCE MANAGEMENT
Transform Performance Management with Process Automation
- Monitor and analyze KPI time-series data from elements & applications
- Unified data collection and analysis in cloud-native environments
- Cloud monitoring for performance across clusters vertically and horizontally without human intervention
- Detects service performance and customer-impacting incidents earlier with machine-learned baselines, machine-learned topologies, and stochastic modelling
- Eliminates multiple teams working on the same root cause through affinity analysis
- Process automation defines root cause, symptoms and population impacted to enable faster action
- Prescribes next best action for incident remediation or prevention
Top-Tier Cable Operator uses VIA Ops to reduce cost and improve DevOps and change assurance processes
TOP-TIER CABLE OPERATOR
Millions of Technician Visits
Reduced Incidents by 65%
PROBLEM:
DevOps, CI/CD and constant network upgrades caused unplanned and undetected outages
IMPACT:
Avoidable truck rolls, poor Net Promoter Scores, service interruption and inefficient staffing
SOLUTION:
Auto-detect CM events, discover dependencies, and correlate to experience KPIs
RESULTS:
Change-related service impact is immediately detected, and truck rolls are avoided
KPI:
More than 200,000 potentially avoidable truck rolls were identified (at a cost of $16M)
FOR CHANGE MANAGEMENT
Transform Change Assurance and Improve DevOps and CI/CD Processes Using VIA AIOps
- Discover dependencies with total ecosystem observability
- Detect change to an entity’s attribute (e.g., subscriber’s device or element’s firmware)
- Correlate alarms, events, incidents and change tickets
- Monitor for and detect customer experience impact
- Automate response with early anomaly detection resulting from change
- Improves CI/CD Processes with the addition of AIOps
Router Failures Diagnosed in a 5G Network Accelerates Incident Response and Resolution Using VIA AIOps
Router Failures Diagnosed in a 5G Network
Accelerate Incident Response and Resolution
PROBLEM:
A cell site router in a 5G radio access network installed remotely becomes isolated, losing connectivity to the broader network infrastructure
IMPACT:
Service is lost for the customers in the affected area. Due to the connectivity loss, the router can’t report that it’s isolated and the issue can’t be detected quickly using traditional monitoring tools
SOLUTION:
VIA AIOps displays the link communication failures, pinpoints the failure location and accurately determines the most likely fix
KPI:
Improved network uptime
FOR 5G NETWORK PERFORMANCE
Detecting Isolated Access Routers Using VIA AIOps
- Restore network outage in affected area quickly.
- Situational knowledge graphs displayed with discovered dependencies showing known and discovered links.
- Generative AI to accurately determine the likely fix.
- Knowing the cause and likely fix reduces remediation time and mitigates the impact of the problem.
- Integration to the IVR system enables auto deflection of incoming customer complaints.
- Ticket triaging to field operations and informing them to dispatch a technician to resolve the issue.
- Customer complaints requiring care agent responses proactively deflected, reducing costs and improving customer experience.
Issues in Application Performance Identified and Resolved Fast
Identify Cause and Resolve Fast
PROBLEM:
Detecting cause of degraded application performance in Kubernetes-based applications
IMPACT:
Application crashes and end user experience issues
SOLUTION:
VIA AIOps identifies memory leaks in Kubernetes-based applications in minutes or hours
KPI:
Improved application performance and user experience
TO IMPROVE APPLICATION PERFORMANCE
Memory Leaks Identified with Cause-and-Effect Relationships Understood
- VIA AIOps platform automatically builds, an ontology for the application technology stack capturing the relationships between the Kubernetes entities (application micro-services, containers, pods and nodes).
- Cause and effects signals are correlated together including service tickets and in-app feedback.
- GenAI and VIA AI with Knowledge™ provides troubleshooting and fix recommendations.