AI/ML Maintenance Orchestration for Cloud Mobile Core Functions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for maintaining cloud-based mobile core network functions require manual intervention from multiple teams, leading to inefficiencies, errors, and potential disruptions due to complex dependencies between network functions, especially in 5G networks, which are not addressed by existing 3GPP standards.
Innovation Solution
A machine learning-driven maintenance orchestrator uses AI/ML techniques to identify and manage dependencies among network functions, enabling semi-autonomous deactivation and reactivation with minimal disruption, by discovering shared cloud infrastructure and defining logical sequences for network function operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual intervention from multiple teams is used for maintaining network functions, then operational control is maintained, but maintenance efficiency decreases and human error increases
Solution Approach 1:
The maintenance orchestrator automatically performs maintenance operations by discovering cloud infrastructure, identifying network functions, and executing deactivation/reactivation sequences without requiring manual intervention from multiple teams, thereby improving efficiency and reducing human error
Solution Approach 2:
The patent replaces manual mechanical processes (human teams performing maintenance) with an automated AI/ML-driven system that uses machine learning models to discover dependencies and orchestrate maintenance operations automatically
2Adaptability or versatility
If cloud infrastructure is shared among multiple network functions, then resource utilization improves, but maintenance complexity increases due to dependencies
Solution Approach 1:
The maintenance orchestrator segments the maintenance process into distinct phases: discovery phase (identifying NFs and dependencies), planning phase (determining deactivation sequences), and execution phase (performing maintenance operations), thereby managing complexity while preserving resource sharing benefits
Solution Approach 2:
The maintenance orchestrator acts as an intermediary between the cloud infrastructure and network functions, automatically discovering and managing dependencies without requiring manual configuration, thus handling complexity transparently while maintaining efficient resource utilization
3Ease of manufacture
If network functions are deactivated for maintenance, then system updates can be performed, but network service disruption occurs
Solution Approach 1:
The maintenance orchestrator performs preliminary actions by discovering cloud infrastructure and identifying all affected network functions before maintenance begins, then plans deactivation sequences to minimize disruption and automatically executes updates with reduced impact on end-user traffic
Solution Approach 2:
The system prepares countermeasures in advance by identifying alternative routing options and dependent NFs before maintenance, enabling rapid restoration of services and minimizing the harmful effects of service disruption during updates
Data Source
AI summary
Aspects of the subject disclosure may include, for example, identifying a set of network functions operative on a core network of a mobile communications system instantiated on a cloud network, identifying functional dependencies among respective network functions of the set of network functions, defining a sequence by which the set of network functions should be made unavailable prior to a maintenance event, wherein the defining the sequence is based on the functional dependencies, and deactivating respective network functions of the set of network functions according to the sequence. Other embodiments are disclosed.