5G Core Signaling Steering Around Fault-Prone Network Functions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional load balancing methods in 5G core networks fail to account for the unique conditions and differences among network functions (NFs), leading to inefficiencies and increased packet loss due to unrecognized software bugs or hardware defects, which are not addressed by generic load balancing approaches.
Innovation Solution
Implementing a network traffic management system that uses machine learning models to identify faulty NFs and UE devices, creating anti-affinity rules to reroute network requests away from problematic NFs and devices, thereby optimizing traffic routing based on feature-specific failure probabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional load balancing methods are used to route network requests, then traffic distribution is simple and fast, but packet loss increases due to unrecognized software bugs or hardware defects in specific NFs
Solution Approach 1:
The system performs preliminary actions by proactively detecting faulty NFs through monitoring their responses and performance metrics before they cause significant packet loss. The anomaly detection mechanism continuously assesses NF health status and pre-computes alternative routing paths, so when a fault is detected, traffic can be immediately redirected without waiting for failures to manifest
Solution Approach 2:
The patent introduces an intermediary component (anomaly detection and routing optimization system) that sits between the conventional load balancer and the NFs. This intermediary monitors NF responses, detects anomalies in their behavior, and intelligently steers traffic away from faulty NFs while maintaining the simplicity of the overall load balancing architecture. The intermediary translates complex fault detection and routing decisions into simple routing rules
2Productivity
If generic load balancing parameters are used for routing, then routing decisions are fast and simple, but routing efficiency decreases because NFs are not identical in practice
Solution Approach 1:
The system applies local quality by treating each NF individually based on its specific characteristics and current state rather than applying uniform routing rules to all NFs. The anomaly detection mechanism monitors each NF's responses and performance metrics separately, identifying specific faults in individual NFs. Routing decisions are then customized for each NF based on its detected health status and performance characteristics, optimizing routing efficiency for the specific conditions of each network function
Solution Approach 2:
The patent dynamically changes routing parameters based on detected NF conditions. Instead of using static load balancing parameters alone, the system adjusts routing decisions based on real-time parameters such as NF response quality, error rates, and performance metrics. The anomaly detection system modifies routing parameters adaptively, steering traffic away from NFs with degraded performance while maintaining simple routing logic through parameter adjustment rather than complex routing rules
3Reliability
If conventional load balancing is used, then system operation is simple, but service success rate decreases due to dynamic and evolving differences among NFs
Solution Approach 1:
The system implements feedback mechanisms where the anomaly detection mechanism continuously monitors NF responses and performance metrics, and uses this feedback to dynamically adjust routing decisions. The system receives feedback from NFs about their operational state, detects anomalies in this feedback, and adapts routing behavior accordingly. This closed-loop feedback system maintains high service success rates by continuously learning from NF performance and adjusting traffic distribution to avoid faulty NFs
Solution Approach 2:
The patent enables the routing system to serve itself by automatically detecting NF faults and making routing decisions without requiring complex external control or manual intervention. The anomaly detection mechanism autonomously monitors NF health, identifies problematic NFs, and automatically steers traffic away from them. The system self-adjusts to changing NF conditions, maintaining high service success rates through autonomous operation rather than complex external management
Data Source
AI summary
Methods, non-transitory computer readable media, network traffic management devices and network traffic management systems that provide for intelligent signaling message steering in 5G core are illustrated. With this technology, a network request is received and a set of features are identified. Based on the set of identified features and a failure probability table, a faulty producer network function (NFs) of a plurality of producer NFs can be identified. A subset of the plurality of NFs that does not include the faulty NF can be defined and the network request can be routed to one of the subset of the plurality of NFs. Accordingly, a network request can be routed away from a NF that, based on the features of the network request, has a relative high probability of resulting in a failure of processing the network request.