Machine Learning and Event Analytics
Provide Intelligent Insights for Better Business Decisions with Assure1
Assure1 understands operational data and behavior patterns because it captures information across service and event data from all direct and indirect sources in your environment.
Quickly pinpoint, analyze and resolve the root cause of service impacting events with Federos’ machine learning and event analytics. Our tools help you eliminate and suppress massive amounts of noise to ensure your IT operations always act correctly against incidents that typically result in impacted services.
With Assure1’s single unified platform, you can align events with their appropriate corresponding analytics models. You’ll use machine learning analytics to generate the best course of action to improve operational efficiencies in real time.
Heterogenous Data Ingestion at Scale
Using its machine learning and event analytics capabilities, Assure1 allows you to take in large amounts of historical and real-time event data at large scale. It provides you with the ability to search and analyze across all faults and realize specific, operational efficiencies.
With machine learning and event analytics, you leverage industry-standard machine learning algorithms with special data filters to normalize data, ensuring correct patterns are fed into the machine learning engine.
Using these data streams, the solution helps you detect anomalies, such as temporal deviations, statistical rarities and unusual behaviors, to generate a singular root causal event in the Assure1 event console. Root causal events contain suppression patterns that filter out noise to improve NOC operators’ rate of predictability to resolve problems versus responding to a storm of event alarms.
Three Use Cases Drive Better Outcomes
Machine learning and event analytics rounds out the three-prong Assure1 strategy for providing customers with industry-leading root cause analysis (RCA). Federos delivers three types of RCA, including:
- Topological RCA by leveraging physical and virtual topology discovery
- Machine learning RCA that learns from patterns and does not require topology
- Human-based RCA where operators can flag noise fields and tie them to known root causes
Federos is providing machine learning and event analytics for three common use cases:
- Event Storms and Dips: Driven by event storms (or sudden dips in events) that are caused by a singular root cause. For example: cut fiber and element management systems disconnect.
- Abnormal Behavior: Driven by learning the noise fields of every device, down to ports on switches. The abnormal behavior rule generates and escalates events based on anomalies not common to that port or device. For example, a core router port that has previously been stable but suddenly begins having issues, would be flagged and escalated for analysis.
- NOC Operational Performance: Looks at how different types of events are handled and learns how each kind of event is managed in the NOC. Based on this information, the solution sends an alert when an event is abnormally handled. For example, if a NOC operator acknowledges a downed port by adding a journal entry and then clearing the alarm, that incident would be “learned” by Assure1 as normal for that type of event. In this case, in the future if someone accidentally cleared an event without working on it, that action would raise an alarm.
Assure1 and the Event Analytics module support physical and virtual devices. By providing the consolidated data in a single source of the truth, Assure1 drives relevant insights that allow operations to continually improve services and business outcomes.
Machine Learning Key Benefits
Cuts through data noise with unprecedented accuracy
Uncovers previously unseen anomalies and root causes from a high volume of faults
Ingests any adjacent data source for deeper learning and pattern matching (e.g. other element management systems data and fault data from other fault management systems)
Improves service quality and customer experience
Opens rules that can be customer modified to find and identify unique environment patterns and develops those patterns into unique rules with no services required
Ingests old event history to pre-train event analytics, allowing for day-one benefits
Extends the value of Assure1 to customers and can be downloaded and deployed into existing Assure1 environments