Fault Handling Service for Network Congestion Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network technologies face challenges in preventing congestion due to faults, such as link failures and control plane faults, which can lead to packet loss and reduced network performance, as they typically react after congestion occurs rather than proactively managing traffic distribution.
Innovation Solution
A fault handling service that configures networks to handle a predetermined maximum number of faults by computing and distributing traffic across paths to avoid congestion, using a sorting networks approach to efficiently model and solve constraints associated with different fault combinations, ensuring that network links do not exceed capacity even when faults occur.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traffic is distributed across multiple paths to handle faults, then network reliability is improved, but device complexity increases due to the need to model and compute traffic distribution for multiple fault combinations
Solution Approach 1:
The patent segments the fault handling problem by dividing it into manageable components: identifying individual link failures, modeling traffic distribution for each failure scenario, and computing paths separately. This segmentation allows the system to handle complexity through systematic breakdown rather than treating all faults as a single undifferentiated problem.
Solution Approach 2:
The patent applies preliminary action by pre-computing traffic distribution patterns and path selections for various fault scenarios before actual failures occur. The system models different fault combinations in advance and establishes routing configurations that can be activated when faults occur, eliminating the need for complex real-time decision-making during actual failures.
2Stability of the object's composition
If the network is configured to handle a predetermined maximum number of faults, then network robustness is improved, but traffic distribution complexity increases due to modeling multiple fault combinations
Solution Approach 1:
The patent applies local quality by focusing traffic distribution computations on local network segments affected by specific faults rather than globally redistributing all traffic. When a link failure occurs, the system computes path adjustments only for flows affected by that specific failure, maintaining simple routing for unaffected portions of the network.
Solution Approach 2:
The patent changes parameters by establishing a predetermined maximum number of faults (k) as a key parameter that defines the scope of robustness. This parameter allows the system to balance between robustness and complexity by limiting the number of fault combinations that must be modeled, thereby controlling the growth of traffic distribution complexity while maintaining adequate network robustness.
3Productivity
If traffic is proactively distributed to prevent congestion, then network efficiency is improved, but computational overhead increases due to modeling and solving constraints for fault combinations
Solution Approach 1:
The patent applies preliminary action by performing traffic distribution computations and path selections before actual faults occur. The system pre-establishes routing configurations for various fault scenarios, so when a failure occurs, the pre-computed paths can be activated immediately without requiring complex real-time calculations, thus minimizing computational overhead during critical moments.
Solution Approach 2:
The patent uses simplified path computation models that can be quickly discarded and regenerated when fault conditions change. Rather than maintaining complex, long-term routing plans, the system computes lightweight path distributions for specific fault scenarios and activates them temporarily, reducing the computational burden of maintaining elaborate routing structures.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The techniques and/or systems described herein implement a fault handling service that is able to ensure that at least part of a network can avoid congestion (e.g., a link exceeding capacity) as long as a predetermined maximum number of faults is not exceeded. The fault handling service models different combinations of possible faults based on network topology and then computes an amount of traffic to be communicated via individual paths such that congestion is avoided as long as a number of actual faults that occur is less than or equal to the predetermined maximum number of faults.