5G Cause Code Handling Using Network Health and Error History
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing 5G standalone core networks face challenges in handling network failures, leading to inefficient resource utilization and service disruptions due to inappropriate cause codes that cause UEs to unnecessarily attempt connections with either the 5G or 4G core networks.
Innovation Solution
Implementing a network device with a machine learning model that processes historical and network health data to determine appropriate cause codes for UEs, optimizing connection attempts based on network conditions and resource availability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If comprehensive error scenarios are handled with accurate cause codes, then service reliability is improved, but but device complexity increases due to machine learning model implementation
Solution Approach 1:
The machine learning model is trained in advance on historical error data and network health data to learn patterns of network failures. This preliminary training enables the model to quickly determine accurate cause codes during runtime without requiring complex real-time analysis, thereby improving service reliability while managing device complexity through pre-computation.
Solution Approach 2:
The patent introduces an Access and Mobility Management Function (AMF) as an intermediary component that houses the machine learning model. This intermediary layer processes error scenarios and determines cause codes between the User Equipment and the core network, isolating the complexity of the ML model within a standardized network function while maintaining reliable service delivery.
2Measurement precision
If machine learning models are used to determine cause codes, then measurement precision is improved, but but use of energy increases due to data processing requirements
Solution Approach 1:
The machine learning model performs the computationally intensive processing in advance during training phases using historical data. During actual network operation, the model makes rapid cause code determinations with minimal energy consumption, achieving high measurement precision while managing energy use through pre-computation of complex patterns.
Solution Approach 2:
The machine learning model continuously learns from incoming error data and network health data, improving its own accuracy over time. This self-improving capability allows the system to achieve high cause code precision while becoming more energy-efficient as the model matures and requires less computational resources for accurate determinations.
3Loss of information
If historical data and network health data are processed, then loss of information is reduced, but but loss of time increases due to data processing
Solution Approach 1:
The machine learning model is pre-trained on extensive historical error data and network health data to capture patterns and relationships. This preliminary processing of large datasets enables the model to quickly determine cause codes during runtime with minimal processing time, reducing both information loss and time loss by performing heavy analysis in advance.
Solution Approach 2:
The patent replaces traditional rule-based error handling mechanisms with a machine learning-based system. The ML model automatically processes and interprets error scenarios without requiring manual rule configuration or complex real-time data analysis, significantly reducing processing time while maintaining comprehensive information utilization through pattern recognition.
Data Source
AI summary
A network device may receive historical data identifying historical error data and error data categorizations associated with a first core network and may store the historical data in a data structure. The network device may receive a request associated with a user equipment and may receive error data from the first core network based on the request. The network device may receive network health data identifying load levels and health of the first core network and a second core network. The network device may determine possible cause data identifying causes associated with the error data based on the historical data, the error data, and the network health data. The network device may generate a cause code for the user equipment based on the possible cause data and may provide the cause code to the user equipment.