Network and service assurance needs are evolving rapidly, as more applications — both network functions that support telecom network operations, and enterprise applications — are becoming virtualized. SNS Research estimates that service provider SDN and NFV investments will have a compound annual growth rate of about 45% through 2020. Such deployments need assurance for both the underlying infrastructure as well as service assurance for the applications they are handling. Meanwhile, networks are also becoming more distributed, with edge computing resources expected to help support the deployment of 5G and low-latency applications.
RCR Wireless News asked a number of companies from around the service assurance space to weigh in, answering the question: What would you consider the “cutting edge” of network/service visibility capabilities right now?  Responses have been lightly edited.
Nicolas Ribault, senior product manager, visibility, Ixia solutions Group, Keysight Technologies:
“Advanced visibility solutions allow you to leverage legacy solutions and adapt to the new architecture and challenges. It is important to look at flows as well as relevant packets from the edge and be able to analyze them in a centralized analytics tool that gives you a comprehensive view of your network. For network service assurance, the ability to combine synthetic monitoring will bring network performance visibility into distributed environments. For application monitoring, looking at process and logs rather than packets will become more efficient. A blend of all these technologies (flow, packets, synthetic) will allow users to find affordable visibility and assurance.”
Sandeep Raina, product marketing director – service assurance, Infovista:Â
“Network and service analytics that provide predictive data for network performance and network capacity, based on machine learning.”
John English, senior marketing manager, NETSCOUT Systems:
“The big focus is on automation, there’s no question about that. It’s a focus for everybody in the NFV/SDN space, because that’s the goal to achieve and realize the promise of virtualization. … There are a lot of projects around automation and AI, and I think that’s really where carriers want to get to: automation. Because that’s going to manage their 5G networks and beyond. You can’t do that on a manual, human basis. And you’re putting out all these new IoT devices and services — these are uncharted waters in terms of their behavior on the network, so having that type of real learning capability and the ability to turn on and turn down resources in response to the changing conditions is critical.
“That’s an area that we’re looking at, as well as, how can we introduce more machine learning and AI into our products, and it’s something we’ll be talking about for awhile.”
Paul Gowans, wireless strategy director at VIAVI Solutions:Â
“Machine Learning (ML) I would consider as ‘cutting edge.’ There are two techniques to ML one is supervised where you are predicting an outcome based on historical data – the data model is mapping an output to an input and looking at anomalies in the model. An example would be trying to predict traffic in a city. However, the more complex ML is unsupervised. This is where you have data sets and you are looking for attributes and behaviors to bring structure to the data set. Location Intelligence visibility is an example of unsupervised machine learning and although very complex once mastered can deliver significant value not only to engineering and operations but also to the business unit’s analytics needs and network monetization.”
Patrick McCabe, senior marketing manager, Nuage Networks:
“Some of the most cutting edge network and service visibility capabilities involves a SDN/SD-WAN multi-cloud infrastructure that spans data centers, public clouds, and connected branches across any WAN transport with full application level visibility and control. Furthermore, companies need an infrastructure that provides a single platform with full network governance from a single pane of glass where service assurance can be programmed across the entire network on a per application basis.
“If I can take a bit of a security angle and apply it to the previous capability of having a full end-to-end view of the network, then ideally this platform has the intelligence to dynamically and automatically take action to respond to known threats to isolate them and neutralize them without any manual intervention pre-programmed as a network policy and instantiated into the intelligence of the network. In addition, having a complete end to end view enterprises can extend the end-to-end micro-segmentation between users and workloads/applications across this hybrid environment which is unique and needed. Nuage’s SD-WAN 2.0 currently has all of the capabilities outlined above.”
Azhar Sayeed, global telecommunications chief architect with Red Hat:
“Ideally, applications and network functions that are refactored to work in virtualized or cloud native environments monitor their own health and take remedial action to restart or scale based on load conditions. The infrastructure must be capable of providing visibility to the state of its health to the applications.
“Another cutting edge solution Red Hat has recently delivered for virtualized infrastructure is to build an assurance framework that allows plugging of various components such as monitoring agents, collectors and even an AI/ML or decision engine to collect, process and push information that can then be used by automation tools to automate the remedial actions.”
Looking for more insights on network and service assurance in virtualized and hybrid networks? Check out the upcoming RCR Wireless News webinar featuring representatives from Vodafone and NETSCOUT, and download our free editorial report.
