NWDAF Analytics Delay Estimation for Timer Expiry Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current 3GPP specifications lack clear guidance on how to handle timer expiries and performance management for Network Data Analytics Function (NWDAF) in wireless communication systems, particularly regarding trained model availability and the time required for machine learning operations, leading to potential errors and inefficiencies.
Innovation Solution
Introduce performance measurement and key performance indicators (KPIs) for NWDAF, including counters to track various scenarios related to timer expiries, and enhance the 'Supported Analytics Delay' attribute to account for data collection, inference, and trained model retrieval times, allowing proactive rejection or negotiation of analytics requests based on network status and request targets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If the analytics producer processes analytics requests with tight time periods, then the response time meets consumer requirements, but the system reliability deteriorates due to timer expirations and errors from insufficient processing time
Solution Approach 1:
The system performs preliminary actions by determining the expected analytics delivery time (DS) in advance of actually processing the analytics request. This allows the system to evaluate whether the requested time period (TA) is sufficient before committing to the analytics generation process, preventing timer expirations and improving reliability while maintaining tight delivery schedules.
Solution Approach 2:
The system implements feedback by using counters to track analytics delivery performance across multiple requests. These counters monitor whether delivery times meet expectations, providing feedback that can be used to adjust and optimize the expected delivery time (DS) parameter, thereby improving both reliability and time management iteratively.
2Reliability
If the system includes comprehensive performance measurement and KPI tracking for NWDAF, then the performance management improves, but the device complexity increases due to additional counters and tracking mechanisms
Solution Approach 1:
The counter mechanism serves multiple functions simultaneously: it tracks analytics delivery timing, monitors timer expiration events, records success/failure metrics, and provides data for performance optimization. This multi-functionality reduces the need for separate tracking mechanisms, managing complexity while comprehensive performance monitoring.
Solution Approach 2:
The system performs self-service by automatically determining expected delivery times (DS) and using tracked counter data to optimize performance without external intervention. The NWDAF autonomously manages its performance measurement, reducing operational complexity while maintaining reliable performance management.
3Measurement precision
If the expected analytics delay (DS) includes machine learning model training time, then the analytics delivery accuracy improves, but the loss of time increases due to additional training requirements
Solution Approach 1:
The system performs preliminary action by determining whether trained models are available before processing analytics requests. When models need training, the system proactively includes the training time in the expected delivery time (DS) calculation, preventing timer expirations and improving time measurement accuracy while managing total delivery time through advance planning.
Data Source
AI summary
There is provided an apparatus comprising: at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to receive, at an analytics producer, a request for analytics, from an analytics consumer, wherein the request comprises a first time period, TA, determine a second time period, DS for an expected time to provide the requested analytics at the analytics producer, provide the analytics based on the request in a third time period, TD, determine, based on TA, DS and TD, which of at least one of a plurality of parameters is met and increment a counter for the determined parameter.