Predictive Route Selection Using Aggregated Node Delay Models

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Delays at routing nodes have become significant with increased network transmission speeds, as they cannot be easily mitigated by improving router interface processing speeds, and route conditions can change before being received by upstream nodes, rendering them less effective for route selection.

Innovation Solution

Implementing aggregating models using artificial intelligence/machine learning (AI/ML) to predict routing performance, allowing for the integration of user devices with network assistance, and supporting control and mobility functionality on cellular links, including direct communication links via NR sidelink, to enhance route selection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional routing methods are used with current network transmission speeds, then bandwidth utilization is improved, but delays caused by routing nodes become significant and cannot be easily mitigated

Engineering Contradiction:

Improvebandwidth utilizationVSAvoidrouting node delay

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent applies preliminary action by having downstream routing nodes generate predictive models of their future routing conditions and send these models upstream before actual routing decisions are needed. This allows upstream nodes to make informed routing decisions based on predicted future states rather than reacting to current conditions, effectively preempting the delay problem by acting in advance.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If routing conditions are queried in real-time, then route selection accuracy is improved, but the conditions change before being received by upstream nodes, rendering them less effective

Engineering Contradiction:

Improveroute selection accuracyVSAvoidinformation transmission time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary action by having downstream nodes predict their routing conditions in advance and communicate these predictions upstream before the actual routing decision point. This eliminates the time lag problem by obtaining routing information proactively rather than reactively, ensuring that upstream nodes have accurate predictive data when making routing decisions.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent uses copying by creating predictive models that replicate or represent the future routing conditions of downstream nodes. Instead of directly querying actual real-time conditions (which would be too slow), the system copies the essential routing characteristics into predictive models that can be transmitted and used for decision-making without the time penalty of real-time coordination.

Inventive Principle:

Principle #26Copying

3Productivity

If more routing nodes are added to increase network capacity, then bandwidth is improved, but delays at individual nodes become even more significant in comparison

Engineering Contradiction:

Improvenetwork capacityVSAvoidrelative node delay

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

As network capacity increases and more nodes are added, the patent's preliminary action approach becomes even more critical. By having downstream nodes generate and transmit predictive models in advance, upstream nodes can make routing decisions that account for future conditions at multiple nodes along potential paths. This proactive approach scales effectively with network complexity, allowing optimal routing decisions even as the number of nodes and possible paths increases.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250385863A1Selecting network routes based on aggregating models that predict node routing performance

Publication Date: 2025.12.18 AT&T INTELLECTUAL PROPERTY I L P

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.