IMS Breakout Path Selection Using ML for Voice Call Quality
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network-to-network voice calls in telecommunications networks suffer from inferior call quality and cost inefficiency due to static route configurations between IP Multimedia Core Network Subsystems (IMS), impacting user experience and operator costs.
Innovation Solution
A system utilizing machine learning models to dynamically determine an optimal breakout path for voice calls by applying path metrics, including quality and cost rankings, and updating these rankings based on call feedback to enhance user experience and optimize costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If static route configurations are used for network-to-network voice calls, then routing simplicity is maintained, but call quality and cost efficiency deteriorate
Solution Approach 1:
The patent implements dynamic route selection by transitioning from static routing configurations to a machine learning-based system that continuously learns and adapts routing decisions. The ML model dynamically selects optimal breakout paths based on real-time and historical call quality data, network conditions, and cost parameters, enabling the routing system to adapt to changing conditions while maintaining operational simplicity through automated decision-making.
Solution Approach 2:
The system incorporates feedback mechanisms where call quality metrics (such as MOS scores, call setup success rates, and drop rates) from actual voice calls are collected and fed back to the machine learning model. This feedback loop enables the model to continuously learn from past routing decisions and their outcomes, improving future routing selections to enhance call quality while maintaining ease of operation through automated optimization.
2Device complexity
If static route configurations are used for network-to-network voice calls, then routing complexity is reduced, but cost efficiency deteriorates
Solution Approach 1:
The routing system performs self-optimization through the machine learning model, which automatically analyzes routing options, call quality feedback, and cost parameters to select optimal paths without requiring manual configuration or intervention. The system serves itself by continuously learning from operational data and autonomously adjusting routing decisions to minimize costs while maintaining or improving call quality, thereby reducing routing complexity management burden.
Solution Approach 2:
The patent utilizes parameter changes by incorporating multiple variables into the machine learning model, including call quality metrics (MOS, setup success rate, drop rate), network conditions, and cost parameters. The model dynamically adjusts routing decisions based on changes in these parameters, enabling cost-efficient route selection that adapts to varying network conditions and operational requirements without increasing routing complexity.
3Reliability
If dynamic route selection with machine learning is implemented, then call quality and cost efficiency are improved, but system complexity increases
Solution Approach 1:
The machine learning model serves multiple functions within the routing system: it selects optimal breakout paths, learns from historical data, predicts call quality outcomes, and optimizes cost efficiency. By consolidating these diverse functions into a single ML-based decision-making engine, the system improves call quality and cost efficiency while managing overall complexity through a unified approach rather than multiple separate systems.
Solution Approach 2:
The machine learning model acts as an intermediary layer between the routing infrastructure and the decision-making process. It receives input parameters (routing options, network conditions, cost data), processes this information through learned patterns, and outputs optimized routing decisions. This intermediary approach encapsulates the complexity within the ML model while presenting a simplified interface to the rest of the routing system, thereby improving performance without proportionally increasing observable system complexity.
4Loss of energy
If dynamic route selection with machine learning is implemented, then cost efficiency is improved, but computational requirements increase
Solution Approach 1:
The machine learning model performs preliminary learning and pattern recognition during training phases using historical routing data and call quality metrics. By pre-learning optimal routing patterns and relationships between parameters before actual routing decisions are needed, the system reduces computational requirements during real-time operation. The model has already processed and learned from large datasets in advance, enabling faster and more efficient routing decisions with lower computational overhead during actual voice call routing.
Data Source
AI summary
Systems and methods for optimizing break-out/break-in paths of voice calls between a source operator's (SO) IP Multimedia Core Network Subsystems (IMS) and a target operator's IMS (TO IMS), the method includes: obtaining a voice call originating from a user equipment (UE) in the SO IMS and terminating at an UE in the TO IMS; determining a routing policy for the voice call; determining an optimal TO Interconnect Session Border Controller (ISBC) by applying at least one path metric according to the routing policy to a machine learning (ML) model for determining an optimal route between the SO IMS and the TO IMS; and route the voice call to the optimal TO ISBC, wherein, the ML model, for determining the optimal TO ISBC using, for each of the path metrics, one or more routing parameter rankings of a plurality of possible paths between the SO IMS and the TO IMS.