Industry Specification Group (ISG) Experiential Networked Intelligence (ENI) Activity Report 2019
Chair: Raymond Forbes, Huawei Technologies
Responsible for developing standards that leverage Artificial Intelligence (AI) mechanisms to assist in the management and orchestration of the network.
The introduction of technologies such as Software Defined Networking (SDN), Network Functions Virtualization (NFV) and network slicing means that networks are becoming more flexible, more powerful – and harder to manage efficiently.
The use of Artificial Intelligence (AI) techniques in the network supervisory and management system can help address some of the challenges of future network deployment and operation.
Our Industry Specification Group on Experiential Networked Intelligence (ISG ENI) develops standards that use AI mechanisms to assist in the management and orchestration of the network. ENI focuses on improving the operator experience, by adding closed-loop AI mechanisms based on context-aware, metadata-driven policies to more quickly recognize and incorporate new and changed knowledge, and hence to make actionable decisions.
By developing standards that use AI mechanisms to recognize new or changed knowledge – and thus make actionable decisions for operators – the work of ENI enables an efficient, intelligence-based deployment of SDN and NFV which will in turn assist the management and orchestration of the network.
The group accordingly considers ENI related issues including architecture, AI, security and Proof of Concept (PoC) frameworks, while coordinating activities with other entities, both internal to ETSI and external.
This approach to network management is illustrated by our recently-released architecture (see below) for the ENI System – an innovative, policy-based, model-driven functional entity that improves operators’ experience. In addition to network automation, the ENI System assists decision-making of humans as well as machines. It facilitates maintenance and reliability of the system that provides context-aware services and thus meet business requirements. For example, with ENI the network can change its behaviour in accordance with changes including business goals, environmental conditions, and the varying needs of end-users. This is achieved by using policy-driven closed control loops – using technologies such as big data analysis, analytics, and AI – to adjust the configuration and monitoring of networks and networked applications.
2019 accordingly saw the publication by ISG ENI of two Group Reports (GR) and three Group Specifications (GS):
- GR ENI 007 V1.1.1 (2019-11) ENI Definition of Categories for AI Application to Networks
- GR ENI 004 V2.1.1 (2019-10) Terminology for Main Concepts in ENI
- GS ENI 005 V1.1.1 (2019-09) ENI System Architecture
- GS ENI 001 V2.1.1 (2019-09) ENI use cases
- GS ENI 002 V2.1.1 (2019-09) ENI requirements
During 2019 work on three PoCs (Proof of Concept) was completed, considering:
- “Intelligent Network Slice Lifecycle Management”
- “Elastic Network Slice Management”
- “Securing against Intruders and other threats through a NFV-enabled Environment”
In addition four further new PoC proposals were accepted by the ENI PoC Review Team:
- “Predictive Fault management of E2E Multi-domain Network Slices” –demonstrates the use of AI for proactive closed loop assurance of the operational capabilities of E2E network slices provided across multiple administrative domains
- “Intelligent Traffic Profiling” - demonstrates the proposed intelligent traffic profiling mechanisms based on Artificial Intelligence/Machine Learning (AI/ML) algorithms
- “Intelligent caching based on prediction of content popularity” - demonstrates the proposed mobile edge caching based on Artificial Intelligence/Machine Learning (AI/ML) algorithms
- “Intelligent time synchronization of network”- demonstrates the proposed intelligent time synchronization of network based on Artificial Intelligence/Machine Learning (AI/ML) algorithms
Learn more about ENI PoC activities at the ENI Wiki.
The ENI Chair contributed with ENI members – along with the Chairs of our ZSM, MEC and NFV ISGs – to a joint white paper titled “Network Transformation; (Orchestration, Network and Service Management Framework)” that was published in October 2019.
During the year ISG ENI participated at these conferences/events:
- Network Automation & AI, London (March 2019)
- ETSI summit on AI, Sophia Antipolis (April)
- 2019 Network Intelligence Forum (organized by China Telecom), Beijing (September)
- SDN/NFV World Congress (Layer 123), the Hague (October)
During 2019 ISG ENI maintained its active liaison with other ETSI groups, including ISG SAI, ISG NFV, ISG ZSM, MEF, ITU-T SG13 and ITU-T FGML5G.
It also continued its involvement in H2020 (including 5G-PPP) research projects, namely SliceNet, 5G-MoNArch and SHIELD. This work has resulted in proofs of concepts to demonstrate the network elasticity mechanisms with a special attention to AI/ML aspects; and how an AI-based network security management framework reacts to different types of threats.
The group also cooperates with the Linux Foundation and other Open Source Communities (OSCs).
Look out for in 2020 – ISG ENI work in progress
- GS on mapping of functional blocks in the ENI architecture and functionalities of the operational systems (e.g. NWDAF, 5GC and NFV MANO)
- Revision to GS (Group Specification) on Proof of Concept (PoC) framework - to coordinate and promote public demonstrations of PoC validating key technical components developed in ISG ENI
- Revision to GS on ENI use cases and scenarios that are enabled with enhanced experience, through the use of network intelligence
- Revision to GS on requirements how intelligence is applied to the network and applications in different scenarios to improve experience of service provision and network operation
- Revision to GS on system architecture – to enhance specification of the software functional architecture of ENI
- GR (Group Report) on intent aware network autonomicity – describes motivation, requirements and key issues of using intent policies to manage the operation of networks and networked applications in various domains
- GR on definition of data processing mechanisms – including data classification, collection, storage, usage and sharing
- GR on evolution method for autonomicity
- Revision to GR on terminology for main concepts in ENI