Feedback-Driven Network Flow Remapping for Congestion Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Congestion in computer networks occurs due to flows colliding and using the same path, leading to switch and link oversubscription, which results in packet delays and drops.
Innovation Solution
A system that analyzes network feedback data to identify congested links and remaps network flows to follow a new path by modifying packet headers, using a remapping probability function to select flows based on congestion levels, and performing hash operations to index packets to available paths.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If multiple flows share common characteristics and follow the same path through the network, then routing simplicity is maintained, but network congestion and link oversubscription occur
Solution Approach 1:
The patent implements dynamic flow remapping that adapts to changing network conditions. The system continuously monitors network feedback data and dynamically remaps flows from congested paths to alternative paths, making the routing behavior adaptive rather than static. This resolves the contradiction by maintaining routing simplicity through automated dynamic adjustment rather than complex manual configuration.
Solution Approach 2:
The system uses network feedback data to monitor congestion levels and automatically remap flows in response to detected congestion. The feedback mechanism enables the system to detect when flows are causing congestion and triggers remapping actions to redistribute traffic, thereby maintaining network productivity while preserving routing simplicity through automated control.
2Productivity
If flows are remapped to reduce congestion by modifying packet headers, then network congestion is reduced, but processing overhead increases
Solution Approach 1:
The system performs remapping only when congestion is detected through network feedback data analysis, rather than continuously remapping all flows. The remapping probability function determines selective remapping based on current network conditions, applying partial action only where needed. This reduces processing overhead while maintaining network throughput by avoiding unnecessary remapping operations.
3Productivity
If a remapping probability function is used to select flows for remapping based on congestion levels, then congestion management efficiency is improved, but system complexity increases
Solution Approach 1:
The system changes the parameter of flow selection by using a remapping probability function that selects flows based on congestion levels rather than arbitrary or static selection criteria. This parameter-based selection improves congestion management efficiency by prioritizing flows that most need remapping, while the probabilistic nature keeps the implementation relatively simple compared to deterministic complex algorithms.
Data Source
AI summary
Techniques and algorithms for monitoring network congestion and for triggering a flow to follow a new path through a network. The network is monitored, and network feedback data is acquired, where that data indicates whether the network is congested. If the network is congested, a feedback-driven algorithm can trigger a flow to follow a new path. By triggering the flow to follow the new path, congestion in the network is reduced. To identify congestion, the feedback data is analyzed to determine whether flows are colliding. The feedback-driven algorithm determines that a network remapping event is to occur in an attempt to alleviate the congestion. A flow is then selected to be remapped to alleviate the congestion.