As artificial intelligence (AI) moves towards the mainstream for telecoms network optimization, one of ETSI’s activities in this area has defined some detailed use cases across the network lifecycle from planning to optimization to predictive analytics.
The Industry Specification Group (ISG) was set up in October 2017 under the label ‘Experiential Networked Intelligence’ (ENI). It defines ‘experiential’ as a method to “observe and learn from the experience an operator has in managing the network, to improve its understanding of the operator experience, over time.”
In other words, AI and machine learning will help the network to learn what impacts on user experience, positively or negatively, and feed that understanding into decisions, to make them more automated and better aligned to real conditions; and into prediction of how the network will behave in future in certain scenarios.
This applies to network planning, operations and maintenance, and also to policy control, service deployment, resource management and monitoring. The use cases which are outlined in the new documents involved infrastructure management (maintenance and planning), network operations, service orchestration and management (such as order-to-activation or SLA management), and assurance (monitoring and prediction). Examples include VoLTE optimization, network slicing for IoT security and SD-WAN management.
The ISG has also published a requirements document covering service and network planning, orchestration, resilience, security and privacy; as well as functions like data collection and analysis, policy management, data learning and interworking; and other issues including regulatory and policy.
This requirements document will be the basis of the system architecture that the group aims to publish next year, seeking to provide operators with a common framework to deploy ENI systems in order to support interoperability in future, reducing cost and complexity.
Huawei has been a prime mover behind ENI. It was originated by the company’s UK-based Dr, Ray Forbes, now its chair, and the firm’s Dr. John Strassner has written a Context-Aware Policy Management Gap Analysis for the ISG. This also draws on work he is doing for the MEF’s Policy-Driven Orchestration (PDO) initiative, which he says meets all ENI’s requirements, except the use of AI to construct policies.
Two other frameworks in this area have been examined – the IETF’s Simplified Use of Policy Abstractions (SUPA), which Strassner says fully or partly meets most of ENI’s requirements; and the TM Forum’s SID (Information Framework), which meets very few.
The first ENI proof of concept will be staged by China Telecom, which provided five of the 26 contributors to the original white paper, and made many inputs to the new documents too. Verizon is planning to contribute a use case and some new requirements. Telefónica, TIM and Vodafone are also members of the ISG, but have not yet committed to a PoC or put their name to the specifications.
On the vendor side, Huawei contributed almost half of the authors of the various documents, while there is involvement from Intel and Samsung, but ENI needs a broader base of support, especially outside China, if it is to be a leading driver of telco AI and the new generation of network optimization.
As in other areas of the new software network, ETSI’s work is either complemented or challenged – depending on your viewpoint – by open source activities, and often these are emanating from the Facebook-initiated TIP (Telecom Infra Project). TIP has launched a new working group focused on AI/ML for telco network management and optimization, co-chaired by Deutsche Telekom and Telefónica. According to Axel Clauberg, DT’s VP of aggregation, transport and IP, it will be “about how machine learning is applied to network management and how artificial intelligence can be used”.
That ties into the overall TIP goal of reinventing the operator network around software, open source and commoditized hardware and introducing an entirely new cost base for telcos. Echoing that, Clauberg said that DT’s goal is to “get better at finding radical approaches to capital efficiency”.
On the ETSI side, Forbes said in a 2018 interview that many operators are incurring unnecessary cost by over-engineering their networks (adding surplus capacity to cope with peak loads) and running services at the least efficient times. He estimates that networks are typically 50% over-engineered, but that AI could reduce that to 10% by allocating resources more dynamically and efficiently according to workload, time of day and geographic patterns.
This would further enhance the resource efficiency impact which operators are already envisaging from virtualization and software-defined networking (SDN), which make it possible to dial network resources up and down on-demand (by calling up new instances of virtual network functions), while an SDN controller orchestrates those VNFs across the whole network.
AI would provide a new level of intelligence and automation for those SDN decisions, while also using machine learning to understand usage patterns in more detail, relating these to network resources, and predicting any faults and failures before they affect user experience.
As China Telecom’s Haining Wang, vice chair of the ENI ISG, put it, while SDN and virtualization are helping to make networks more flexible, management complexity remains as high as ever – it is just transferred from hardware to software.
“It’s making resource management less human dependent in terms of knowledge,” Forbes said. “You want to have a business analyst who just performs data models; you don’t want to have a lot of pre-thinking and management analysts that analyze what to do.”
At the heart of ENI’s approach will be context awareness – the goal of many 5G-related projects, which envisage a whole new wave of mobile experiences, and revenue-generating services, which derive from the networks’ precise knowledge of a user’s context, preferences and habits.
The group says it will define an AI-enabled context aware system based on the ‘observe-orient-decide-act’ control model, which allows a system to adjust the services it is offering according to changes in user requirements, environmental conditions and business goals. This system will result in standardized models for using AI to manage a network and intelligently control service delivery and user experience.
The automated system will learn from previous experience and so add intelligence to automated network planning and monitoring, reducing opex, improving capacity usage, and boosting user experience, to a greater extent than just using automated technologies like self-optimizing network (SON).
The group will also study network telemetry, big data mechanisms, machine learning, and how to simplify and scale complex device configuration and monitoring.
“The unique added value of the ETSI ISG ENI approach is to define new metrics to quantify the operator’s experience; this enables the optimization and adjustment of the operator’s experience over time, taking advantage of machine learning and reasoning,” said Forbes when the ISG was announced in April 2018.
Adding AI to the mix promises to make automation intelligent, and so deliver better results, but it will also slow down the process of getting to the self-driving, fully software-driven telco network. AI and ML cannot be rushed – they are of their nature slow to perfect because the models need to learn until they reach the stage where they can make quicker, better decisions than a team of trained experts. “You need to design a model and spend a bit of time teaching the model how to do things,” Forbes said.
Forbes believes the dream of “fully AI-based autonomics” is far away, though ENI is taking steps in that direction. “The ultimate aim is to improve the user experience and simplicity to have intent-based network indications in line with customer demand for new revenue,” he concluded.