More and more, successful businesses rely on the ability to access and analyse vital data and respond accordingly to changing market conditions. Machine learning and the application of Artificial Intelligence is revolutionising the ability to manage services — as long as they can extract the right data. Yuval Stein, AVP product management, Service Assurance at Teoco explains how contextual service assurance will be critical to satisfy the demands of business and deliver the full promise of 5G.
The hunger for access to data puts enormous pressure on the communications service provider. In telecoms, ‘service assurance’ used to mean just that a connection was available. Today, availability is not enough. Service providers need to guarantee more — the speed of the line, its capacity, and the back-up routes and systems that maintain agreed performance standards in the event of failure. But even this definition is about to get a whole lot more complex.
The 5G promise
One promise of a 5G network is that it is more than one network. With 5G slices CSPs will be capable of offering different levels and types of service. These various slices will support different customers and devices, with different applications and differential tariffing. Each slice and solution will have specific service assurance requirements.
The range of 5G services being developed stretches from supporting small gadgets in the home to systems that can guide heavy loads around vast factory floors; from immersive VR to wearable tech that can save lives. 5G, as an enabler of massive-scale Internet of Things uptake, presents service providers with an opportunity and challenge, both technically and from a service delivery standpoint. Realising the benefits requires an approach that fundamentally changes how networks are designed, delivered, managed and accessed.
Contextualising the service
How do you manage the network to assure the right level of service is maintained across one type of functionality within a network slice, without adversely affecting performance elsewhere? If the resource is finite, allocating more of it to one service could affect the customer satisfaction elsewhere. That’s why operators need to master the art of contextual service assurance.
Addressing this challenge is a priority for operators — enterprise customers will demand reliable, guaranteed data connectivity across 5G networks to drive their businesses. The rule that successful business relies on its data applies to service providers just as it applies to their enterprise customers.
Understanding the impact
Contextual service assurance in a 5G network means the ability to monitor a horizontal infrastructure running multiple service types that can be dynamically requested, scaled and terminated. This network will also handle even larger data volumes than today — both customer traffic and network signaling — that most traditional service assurance tools and manual oversight by engineers of the network will find it hard to cope with.
In a cloud-supported 5G network, the impact of one service type must be understood, managed, and adjusted according to its context — the importance of the service, its likely duration and performance requirements, plus the availability of resources and prevailing network conditions.
Because the economic case for deploying a 5G network depends on its ability to extend and support the co-existence of various service types, solving the contextual service assurance challenge is fundamental to the return on the 5G investment.
Managing each slice
A network slice is effectively a self-contained virtual network, free of many of the constraints of a hardware-dependent network and therefore relying on virtualisation infrastructures. Each slice must meet both SLA and operating level agreement (OLA) thresholds determined by the customer and the provider. Thereafter, the service management and assurance must be applied on a per slice basis. This is particularly important for a slice that is event related — resource heavy but frequently dormant — and where context really is king for network management.
Service assurance tools must be able to correlate service experience with underlying resource, ensuring that no slice is demanding more than it is planned to provide — and capacity is available to boost services when required. Different services will have different thresholds. Some of these will be hard — in low-latency or ultra-reliable services for example – while others will have more flexibility. Managing this co-existence and interplay between slices lies at the heart of contextual service assurance.
AI to the rescue
That’s where both machine learning and AI can come to the rescue. Machine learning can identify patterns of behavior, driving AI-assisted network automation, reducing the need for human oversight. The goal is ‘closed-loop’ automation — but operators are often risk averse, reluctant to trust mission-critical infrastructure to automation without evidence of reliability. We foresee plenty of sandbox testing to prove that service providers can reap the benefits of automation.
The diverse range of 5G-based service types that are under development — crucial to the long-term health and profitability of service providers—cannot be delivered without mastering contextual service assurance.
The 5G network platform introduces new technologies in radio, in the core, and in software defined transport, creating a more dynamic networking environment. Only contextual service assurance is guaranteed to meet the automated, closed-loop, network optimisation required to enable operators to meet SLAs on a service-by-service, network slice-by-network slice basis.
The author of this blog is Yuval Stein, AVP product management, Service Assurance at Teoco
Comment on this article below or via Twitter: @VanillaPlus OR @jcvplus
