Avanseus™ Cognitive Assistant for Networks (CAN) predicts potential communication and IT network failures & service degradations and recommends preventive measures to help proactively manage the legacy, NFV & Hybrid Networks. VNFs, CNFs, and Network slices are monitored automatically for performance and resources adjusted to make sure the agreed SLA is delivered. It helps detect service degradation or poor network performance signals that cannot be identified by existing network monitoring systems and uses advanced machine learning to continuously extract ever improving information from Network functions and resources to proactively configure the network resources for meeting SLA. Technology and network vendor agnostic, CAN is suitable for Communication Service Providers, Managed Services Providers, Tower Companies, Broadband Providers and enterprises using IoT. More importantly, CAN helps in smooth 5G evolution by enabling automated & agile operations.
Prediction of Network incidents in advance
The Avanseus CAN (Cognitive Assistant for Networks) platform automatically predicts potential events or failures in the network 7 to 30 days in advance (configurable) and recommends the root cause of the failure based on historical fault patterns and aid NOC and field teams to effectively manage these impending failures by proactively performing preventive actions. Operators benefit from reduced cost of network maintenance, smart capex management, better customer experience and improved SLA adherence for enterprise customers.
Prediction of KPI Degradation
The platform automatically predicts network KPIs such as latency, throughput and identify the potential threshold violation cases. The platform further correlates the potential KPI violation cases with predicted network faults to provide a comprehensive insight on impending faults and deep insights on root cause. This sets the foundation for VNF and ‘network slice’ degradation prediction use cases.
AI driven automated trigger for self-healing and auto-scaling of network slices
While 5G and Telco cloud will have large scale implementation of NFVs running on commodity hardware, the downsides are virtualised network functions (VNFs) and their host commodity servers are more failure prone than dedicated hardware, and virtualization introduces more layering and less visibility into lower layer faults. One question critical to the success of NFV systems is whether it can provide availability similar to that of traditional carrier-grade systems, with up to five 9s (99.999% of uptime). Also, the exponential increase in number of VNFs will lead to high cost of network operations, if not handled automatically. The key is to monitor the end to end service quality where the service will include multiple cross vendor VNFs. Here, tight SLA is expected & less time is available for decision making. To achieve this, cross vendor self-healing & auto scaling is needed.
AI driven orchestration for cross vendor VNF self-healing & auto-scaling is the only answer to these challenges. Only an instantaneous prediction mechanism can work in dense 5G network due to high density of VNFs & very large amount of PM KPI, configuration & probe data.
Avanseus provides ‘Instantaneous Prediction’ which is event driven in real time. Prediction is in the form of ‘Health Index’ not only at the individual VNF level but also at the ‘service’ level. Health Index is a numerical value denoting the health of a VNF or CNF or a service. The value is limited within 0 and 100, 0 being the worst and 100 being the best. This value is calculated for each prediction at an individual factor level, the factor being a KPI of VNF, then aggregated at VNF level and further aggregated at service level. This enables continuous monitoring & prediction of end-to-end service quality across vendor specific VNFs. The prediction engine is very fast to cater to the exponential increase in VNFs.