ETSI GANA as Multi-Layer Artificial Intelligence (AI) Framework for Implementing AI Models for Autonomic Management & Control (AMC) of Networks and Services; and Intent-Based Networking (IBN) via GANA Knowledge Planes (KPs)

This Technical White Paper No.4 is about Demo-4 (of a series of Demos planned for 2018/2019 and beyond) of the ETSI PoC (Proof-Of-Concept) on 5G Network Slices Creation, Autonomic & Cognitive Management and E2E Orchestration; with Closed-Loop (Autonomic) Service Assurance for Network Slices; using the Smart Insurance IoT Use Case.

The Technical White Paper covers the following key topics in the target of operationalizing the ETSI GANA Model Standard (ETSI TS 103 195-2) in the context of 5G Networks and reveals Gaps in Standards that should be addressed by the industry while implementing GANA autonomics (control-loops) in network architectures and associated management and control architectures. The following aspects are covered in the results of the PoC:

• Towards a “Market Place” for GANA Cognitive Decision-making Elements (DEs) as Procurable and Deployable AI Models (powered by Algorithms for Machine Learning (ML), Deep Learning (DL), Computational Intelligence, etc.) for realizing the AMC Paradigm
• “Ated_Amic_Amous” (“3As”): Automated Management vs Autonomic Management & Control vs Autonomous Network Behaviour: Taxonomy Harmonization
• ETSI GANA Model as Multi-Layer Artificial Intelligence (AI)/Machine Learning (ML) Reference Model for Autonomic Management & Control (AMC) of Networks and Services 3. Implementation Approaches for GANA DEs and their associated Control-Loops
• Cognitive-GANA-DE (AI Model) Vendor(s), Autonomic Management & Control Domain Expert(s), and Data Scientists, as Stakeholders bound by a DEs Production Ecosystem
• ETSI GANA AMC_DEs (AI/ML Models) Marketplace Concept and Scope
• The AMC Concept powered by AI/ML Capabilities
• Lifecycle Management Framework for a Cognitive GANA DE as an AI/ML Model for realizing specific AMC Objectives
• Modeling the Interfaces and Primitives/Operations for Enabling Programmability (Manageability) of a Cognitive GANA DE (a Deployable “AI Model” software component for specific AMC targets)
• How the ITU-T ML Framework (ITU-T Y.3172) can be applied in implementing the ETSI GANA Cognitive DEs for Autonomic Management and Control (AMC)
• GANA Cross-Layer Autonomic & Cognitive Business-Service-Network Framework and the Benefits and Value Creation the Framework brings, and AMC/Self-Management Use Cases Description Template