Subscriber-Aware Session Release with Adaptive Inactivity Timers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing 5G/IoT network resource utilization is inefficient due to unnecessary occupation during ongoing sessions with no usage or signaling, leading to suboptimal resource allocation and potential revenue loss for service providers.
Innovation Solution
Implementing a system that uses historical usage data to determine an optimal 'Unit Count Inactivity Timer' for communication sessions, leveraging a Network Data Analytics Function (NWDAF) to generate an idle score for subscribers, allowing the Charging Function (CHF) to set an appropriate timer value, thereby optimizing resource utilization and release operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If a fixed inactivity timer value is used for all subscribers, then the system is simple to operate, but network resources are unnecessarily occupied during idle sessions
Solution Approach 1:
The patent applies dynamics by making the inactivity timer value adaptive rather than fixed. The system dynamically adjusts the timer based on subscriber behavior patterns, service types, and historical data. This allows the timer to optimize network resource utilization for each specific case while maintaining automated operation through behavioral analysis.
Solution Approach 2:
The patent changes the parameter of inactivity timer value from a static configuration to a dynamic parameter that varies based on subscriber characteristics, service types, and predicted behavior. This parameter adaptation enables fine-tuned resource management without requiring complex manual intervention for each scenario.
2Loss of energy
If network resources are released quickly during idle sessions, then resource utilization is optimized, but service availability may be reduced for legitimate ongoing sessions
Solution Approach 1:
The patent applies preliminary action by analyzing subscriber behavior patterns and predicting future activity before making resource release decisions. The system uses historical data and machine learning to forecast when a subscriber is likely to resume activity, allowing it to extend timer values proactively for predicted active sessions while releasing resources for genuinely idle sessions.
Solution Approach 2:
The patent implements feedback mechanisms where the system continuously monitors subscriber activity, compares actual behavior against predictions, and adjusts timer values accordingly. This closed-loop approach ensures that resource release decisions are continuously optimized based on real-time observations, maintaining service availability while improving resource utilization.
3Productivity
If personalized inactivity timer values are assigned to each subscriber, then resource utilization is optimized, but the system complexity increases
Solution Approach 1:
The patent applies self-service by enabling the system to automatically determine and adjust inactivity timer values for each subscriber without manual intervention. The machine learning models and behavioral analysis algorithms autonomously process subscriber data, generate predictions, and configure appropriate timer values, eliminating the need for complex manual configuration while achieving personalized optimization.
Solution Approach 2:
The patent introduces an intermediary layer consisting of behavior analysis functions and machine learning models that bridge the gap between raw subscriber data and timer configuration decisions. This intermediary automatically processes information, applies optimization logic, and generates configuration parameters, reducing the apparent complexity for operators while enabling sophisticated personalized resource management.
Data Source
Figure 1~2
Figure 3~4
Figure 5~6
AI summary
A network node of a communications network performs operations to determine a data traffic inactivity timer value based on subscriber event data, which identifies a subscriber and service characteristics using a communication session, being processed through a predictive model which uses historical usage data indicating idle times previously measured by charging trigger functions (CTFs) for the subscriber and the service characteristics. The operation further communicate the data traffic inactivity timer value to a CTF to configure monitoring of inactivity of the service using the communication session and to trigger a release operation related to the communication session when a data traffic inactivity timer using the data traffic inactivity timer value is determined to expire based on the monitored inactivity of the service.