By - Raghvendra Singh Yadav, Delivery Head, APAC, Teoco
Automation is the sine qua non of 5G networks. That's because networks, systems, and business processes that support it will require lightning-speed decision-making for its benefits to be fully realised. 5G networks are too complex, too big, and too critical to be managed manually. As most often, 75% of network downtime is caused by human error, automation is no longer optional. It’s also no longer just about cutting costs and reducing headcount. Autonomous networks at this point in time are critical, and “intent-based networking” is the new-kid-on-the-block.
This new concept for mobile service providers requires complex automated decision-making that decouples the “what” from the “how”. Intent-based networking helps by allowing for the customisation of services at the management layer. Different organisations, including business operations on the customer side and network service and resource operations on the service provider side, can now specify their intentions for what they want.
It involves participation from the business customer to help define their needs: what service or application they need and what properties those services require, such as cost, latency, or uptime.
These needs, of course, will vary depending on the use case. This brings us to the question—what logic governs "intent" in autonomous networks? When a combination of artificial intelligence (AI), network orchestration and machine learning (ML) algorithms come together to automate routine functions, the network becomes more intelligent, autonomous and clever in adapting to changing workloads. The result is a more flexible and scalable network that can deliver a superlative performance.
Inadequacy of Traditional Methods and Tools
We are entering a stage in the lifecycle of 5G networks where manual and static programming and rules-based automation have outlived their utility. Today, business, service, and network operations have become increasingly complex as services become more dynamic, fragmented, and distributed.
While differentiated services better meet customers’ increasing demands, they also add to the overall complexity. Add to this the promise of more lucrative revenue streams for network operators, and the scenario gets even more complicated.
This growth on steroids seems to outpace the operators’ abilities to oversee, control and assure customer experience, service operations, cost, and network performance via the use of traditional methods and tools. What’s needed, therefore, are model and knowledge-based approaches that are
formed on the basis of the intent behind business, service and resource requirements and constraints.
This brings in the advantage that services can be transformed and developed more autonomously as business strategies, goals and customer requirements change.
Need for the Digital Transformation of Telecom Networks
With growing network complexity, the digital transformation of networks becomes a necessity. Operators need to leverage the latest technological advancements in 5G, AI, IoT, cloud and edge computing as they are already being adopted globally by key enterprise verticals in support of their specialised business needs. Telecom, therefore, can’t be left behind. Autonomous networks based on the emerging technologies of AI, ML, etc., will provide operators with the opportunity to bring in meaningful service quality improvements as well as unlock significant revenue growth.
Manual and labour-intensive methods that were traditionally employed to manage the network and services will no longer be sustainable in a 5G environment. In the absence of automation, therefore, operators will find it difficult to maintain their competitive advantage and deliver high-quality services to their customers. Note here that automation can’t be done in parts. The only viable option to overcome the challenges associated with the dynamicity of modern networks is full automation. The answer lies in closed-loop network automation, which is self-healing and self-scaling. This will usher in greater network stability and performance, the near complete elimination of human intervention, a simplified service design, improved service parameters, and the ability to react to network events in real-time to avoid outages.
This brings us to the concept of intent-based management. An intent-based model promotes greater separation of tasks and clarifies roles between the “owner” of the intent and the “handler” of that same intent. In this scenario, the intent is the expression of the requirements that an autonomous network party needs to meet, making it a key concept in the establishment of an advanced, highly capable, intelligent network. The intent will typically be passed between different management domains enabling each one of them to work autonomously.
Autonomous Networks Enable Rapid Service Innovation
For operators to stay aligned with their customers requirements and meet their evolving expectations, it’s critical to automate the operations of complex and dynamic cloud-native networks efficiently. Autonomous networks will enable operators to handle the complexities of orchestrating network
resources to enable rapid service innovation. They will also be able to harmonise the assurance and orchestration resources so that the whole network is unified and synchronised in its autonomy through closed-loop automation.
AI/ML: Technologies Behind Autonomous Networks
To understand why autonomous networks can do what they do, let’s understand the role of AI and ML in it. These emerging technologies are key enablers of the closed-loop automation concept that is intrinsic to autonomous networks. These intelligent algorithms can handle complex decision-making, which is required to configure and optimise network resources and orchestrate services. This is implemented in a way that changes made to the network are not disruptive to other areas of the network. In future, ML and AI are expected to enable predictive operations. These algorithms will be able to spot patterns that emerge from network service degradations. Further, they will be able to employ automated remediation routines to adjust the network parameters, with the overall aim of reducing downtime and increasing the quality of service.
Intent-based management compliments ML and AI technologies within the context of autonomous networks. It helps to separate the ownership of management goals from implementation details; the actors that need to understand the “what” do not need to be concerned with or understand the “how”. By creating a language that is straightforward for both owners and handlers to understand, it creates the space for new standards to emerge, that is, the ability to express intent. This creates an open ecosystem that reduces dependency on specific vendors, opens up the market for new,
disruptive players foster innovation and reduce costs.
Today, it’s not difficult to create highly capable autonomous networks since technologies exist and are within reach. As the arrival of 5G increases the complexity of networks that operators must grapple with, human intervention goes out, and automation with intent-based management moves in. This can help network operators to optimise their networks with efficiency and minimalism and achieve more with less. It's time operators begin using intent when designing their autonomous networks to be able to deliver 5G and its advantages to their customers.