Aggregated Node Models for Predictive 5G Route Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Delays at routing nodes in network communication systems have become significant due to limited processing speeds, especially with increased network speeds and changing routing conditions, making traditional route selection methods less effective.
Innovation Solution
Implementing aggregating models that predict routing performance using artificial intelligence and machine learning to select optimal network routes, incorporating predictive models from connected nodes and updating them with feedback for improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional route selection methods are used, then device complexity is reduced, but routing performance and reliability deteriorate due to delays at routing nodes
Solution Approach 1:
The patent applies preliminary action by having routing nodes generate predictive models of their future performance conditions in advance. These models predict delays, available bandwidth, and other routing metrics for future time periods, allowing upstream nodes to make informed route selection decisions before actually transmitting data, thus avoiding the delay problem without requiring complex real-time monitoring infrastructure.
Solution Approach 2:
The patent uses predictive models as intermediaries between the actual routing node conditions and the route selection decision. Instead of directly monitoring and reacting to real-time node conditions, upstream nodes receive and process these predictive models that mediate the information flow, enabling better route selection while maintaining relatively simple device complexity.
2Reliability
If real-time routing condition monitoring is implemented, then routing performance improves, but loss of time occurs because conditions change by the time route selection is made
Solution Approach 1:
The patent resolves this contradiction by performing the routing condition assessment in advance. Routing nodes generate predictive models that forecast their performance for future time periods, allowing upstream nodes to select optimal routes before traffic conditions change. This eliminates the time loss associated with real-time monitoring while maintaining accurate routing decisions.
Solution Approach 2:
The patent implements feedback mechanisms where routing nodes provide predictive models to upstream nodes, and upstream nodes use these models to select routes. The system also incorporates feedback from actual routing performance to update and refine the predictive models over time, improving accuracy while maintaining the time-efficient advance planning approach.
3Measurement precision
If predictive models are aggregated from multiple nodes, then measurement precision of routing conditions improves, but device complexity increases
Solution Approach 1:
The patent applies merging by combining predictive models from multiple routing nodes into aggregated models at upstream nodes. This consolidation allows upstream nodes to assess the overall performance of different route options by integrating information from all constituent nodes, improving measurement precision while using standardized aggregation algorithms that control complexity.
Solution Approach 2:
The patent implements universality by designing predictive models with standardized structures and formats that can be universally applied across different routing nodes. This multi-functionality allows the same model framework to be used throughout the network, simplifying the aggregation process and reducing device complexity while maintaining high measurement precision through comprehensive node coverage.
Data Source
AI summary
The technologies described herein are generally directed to selecting network routes based on aggregating models that can predict routing performance in a fifth generation (5G) network or other next generation networks. For example, a method described herein can include communicating, to second routing equipment, a first model describing a delay predicted to be caused to a future communication by the future communication being transited via the first routing equipment. The method can further include receiving, from the second routing equipment, a current communication for transit via the first routing equipment to destination equipment, wherein the first routing equipment was selected by the second routing equipment based on the first model, and second models, other than the first model, describing respective predicted delays from other routing equipment other than the first routing and second routing equipment.