Cross-Domain Analytics Correlation for 5G Policy Triggers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing communication systems face challenges in effectively combining and correlating analytics from different domains such as RAN, 5G core, and OAM, leading to sub-optimal inference and training due to differing time scales and scopes of data collection, which affects prediction accuracy and policy determination.
Innovation Solution
A method and apparatus for comparing and correlating analytics between different data analytics functions, using triggering conditions based on deviations and thresholds to enhance insight and improve prediction accuracy by combining data from RAN, 5G core, and OAM, allowing for more informed policy decisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If analytics from different domains (RAN, 5G core, OAM) are collected independently with different time scales and scopes, then each domain can maintain its own data collection efficiency, but the prediction accuracy and policy determination become sub-optimal due to lack of correlation
Solution Approach 1:
The patent combines analytics from multiple domains (RAN, 5G core, OAM) into a unified analytics framework. The consumer NF correlates analytics results from different producer NFs by comparing deviations and applying triggering conditions, effectively merging previously independent data streams into a coordinated system that improves prediction accuracy while maintaining collection efficiency.
2Adaptability or versatility
If analytics are collected with different time scales and scopes across domains, then each domain can operate autonomously, but the correlation between analytics becomes difficult leading to sub-optimal inference
Solution Approach 1:
The patent implements a feedback mechanism where the consumer NF receives analytics results from producer NFs, compares them against expected deviations, and triggers requests for additional analytics when thresholds are exceeded. This feedback loop maintains domain autonomy while recovering correlation information that would otherwise be lost due to different time scales and scopes.
Solution Approach 2:
The consumer NF acts as an intermediary between different producer NFs (RAN, 5G core, OAM domains). It receives analytics from various domains, correlates them by comparing deviations, and determines when triggering conditions are met, thereby mediating the correlation between autonomous domains without requiring them to directly coordinate.
3Device complexity
If multiple analytics functions operate independently without coordination, then system complexity is reduced, but the ability to determine accurate policies and predictions deteriorates
Solution Approach 1:
The patent segments the analytics system into distinct producer NFs and a consumer NF, where each producer maintains independent operation reducing coordination complexity. The consumer NF then segments the correlation process by evaluating deviations from expected analytics results and applying triggering conditions selectively, rather than requiring continuous coordination between all components.
Data Source
AI summary
There is provided an apparatus comprising means for: receiving, at a first data analytics function from a second data analytics function, configuration information for obtaining a first set of analytics, wherein the configuration information comprises a triggering condition for reporting the first set of analytics, wherein the first analytics function is configured to utilise a first set of input data for obtaining the first set of analytics and the second analytics function is configured to utilise a second set of input data for obtaining the second set of analytics; based on the configuration information, obtaining the first set of analytics based on the first set of input data; determining that the triggering condition is satisfied; and in response to determining that the triggering condition is satisfied, sending, to the second data analytics function, the first set of analytics.