Dynamic Service-Level Adjustment for Deterministic Network Delay

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional best-effort-based IP networks fail to provide deterministic service forwarding capabilities, particularly for ultra-reliable low-latency communication (URLLC) services, which require guaranteed end-to-end delay and packet loss prevention, leading to suboptimal network resource utilization.

Innovation Solution

A service level adjustment method that dynamically adjusts queue resource parameters and data flow constraints based on real-time queue status information to ensure end-to-end delay requirements while optimizing network resource utilization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional best-effort-based IP network is used, then network operation simplicity is maintained, but deterministic service forwarding capability and end-to-end delay guarantee cannot be provided

Engineering Contradiction:
Improveend-to-end delay guaranteeVSAvoidnetwork control complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent implements dynamic service level adjustment by continuously monitoring queue status information and adapting service level parameters in real-time. The network device adjusts queue resource parameters and data flow constraints dynamically based on current network conditions, transforming the static best-effort forwarding into a dynamic system that can guarantee end-to-end delay while maintaining operational simplicity.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes key parameters of service levels including queue resource parameters (buffer size, bandwidth allocation) and data flow constraints (thresholds for burst amount and average rate). By adjusting these parameters based on monitored queue status, the system achieves deterministic forwarding guarantees without requiring complex manual configuration.

Inventive Principle:
Principle #35Parameter changes

2Reliability

If service level parameters are adjusted to ensure end-to-end delay, then delay guarantee is improved, but network resource utilization may deteriorate

Engineering Contradiction:
Improveend-to-end delay complianceVSAvoidnetwork resource utilization
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system dynamically adjusts service level parameters based on real-time queue status monitoring. When queue status indicates sufficient resources available, the system relaxes constraints to improve resource utilization. When queue status shows resource exhaustion or delay violations, the system tightens constraints to ensure delay guarantees. This dynamic adaptation resolves the contradiction between delay guarantee and resource utilization.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent implements a feedback mechanism where queue status information is continuously monitored and used to adjust service level parameters. The system measures actual queue depth, packet loss rates, and delay metrics, then uses this feedback to optimize parameters. This closed-loop control ensures delay compliance while maximizing resource utilization by avoiding overly conservative static configurations.

Inventive Principle:
Principle #23Feedback

3Reliability

If queue resource parameters are increased to meet delay requirements, then delay guarantee is improved, but network resource overhead increases

Engineering Contradiction:
Improvepacket loss preventionVSAvoidnetwork resource consumption
Core Design Contradiction:
ReliabilityVSQuantity of substance

Solution Approach 1:

The patent adjusts queue resource parameters (buffer size, bandwidth allocation) and data flow constraints dynamically based on monitored network conditions. Instead of allocating excessive resources statically, the system changes parameters adaptively - increasing buffer size or bandwidth only when and where needed to prevent packet loss, while reducing allocations elsewhere to minimize overall resource consumption.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system applies different service level parameters to different queues and data flows based on their specific requirements and current status. Rather than uniformly increasing resources across the entire network, the patent implements local optimization where queue resource parameters are adjusted only for specific queues that need them, leaving other queues with appropriate minimal allocations.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP4080829B1Service class adjustment method, apparatus, device and storage medium
Publication Date: 2025.07.30 HUAWEI TECH CO LTD
  • EP4080829B1 patent drawingFigure 1
  • EP4080829B1 patent drawingFigure 2
  • EP4080829B1 patent drawingFigure 3

AI summary

A service level adjustment method and apparatus, a device, and a storage medium are provided. The method includes: A first network device obtains at least one piece of queue status information at a target service level of the first network device (401). When any one of the at least one piece of queue status information exceeds a first threshold upper limit corresponding to the any queue status information, the first network device adjusts a parameter of the target service level based on a maximum delay associated with the target service level (402). When the queue status information at the target service level exceeds the corresponding threshold upper limit, the first network device adjusts the parameter of the target service level based on the associated maximum delay, so that network resource utilization is further improved while an end-to-end delay of a service is ensured.