ECN Inference Model for Adaptive Network Congestion Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current network congestion control methods using explicit congestion notification (ECN) mechanisms suffer from low flexibility due to statically configured ECN thresholds, leading to either excessive queue depths or low network resource utilization.
Innovation Solution
Implement a dynamic congestion control method where network devices input status information into an ECN inference model to obtain an updated ECN configuration parameter, allowing for adaptive threshold adjustments based on real-time network performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If the ECN threshold is set to an excessively high value, then the queue depth of the egress queue in the network device is relatively large, but the transmission delay of a data packet is relatively large
Solution Approach 1:
The patent applies dynamics by transitioning from static ECN threshold configuration to dynamic adjustment. The network device continuously monitors queue depth and transmission delay, automatically adjusting the ECN threshold in real-time to adapt to changing network conditions, thereby resolving the contradiction between maintaining adequate queue depth and minimizing transmission delay
Solution Approach 2:
The patent implements parameter changes by modifying the ECN threshold parameter based on real-time network status. The system changes the threshold value dynamically according to monitored metrics such as queue depth and transmission delay, allowing the network device to optimize performance by adjusting this critical parameter in response to actual network conditions
2Productivity
If the ECN threshold is set to an excessively low value, then the rate at which the transmit end sends a data packet is relatively low, but network resource utilization is relatively low
Solution Approach 1:
The patent applies feedback by implementing a closed-loop control system that continuously monitors network resource utilization and data packet sending rate. The network device receives feedback about actual network conditions and uses this information to adjust the ECN threshold, thereby optimizing both productivity and resource utilization in a continuous feedback cycle
Solution Approach 2:
The patent uses dynamics to enable the ECN threshold to adapt to varying network conditions. By making the threshold dynamic rather than static, the system can respond to changes in network traffic patterns and resource availability, simultaneously improving data packet sending rate and maintaining high network resource utilization
3Stability of the object's composition
If the ECN configuration parameter is statically configured, then the network device operates with fixed thresholds, but flexibility of current network congestion control is relatively low
Solution Approach 1:
The patent resolves this contradiction by making the ECN configuration dynamic. The network device continuously adjusts the ECN threshold based on real-time monitoring of queue depth and transmission delay, transforming the static configuration into a dynamic adaptive system that maintains stability through continuous optimization while achieving high flexibility in congestion control
Solution Approach 2:
The patent implements self-service by enabling the network device to automatically adjust its own ECN configuration without external intervention. The device monitors its own performance metrics and autonomously modifies the ECN threshold to optimize congestion control, thereby achieving both configuration stability and operational flexibility
Data Source
AI summary
A network device inputs first network status information of the network device in a first time period to an ECN inference model, to obtain an inference result that is output by the ECN inference model based on the first network status information. Then, the network device sends an ECN parameter sample to an analysis device that manages the network device, where the ECN parameter sample includes the first network status information and a target ECN configuration parameter corresponding to the first network status information, and the target ECN configuration parameter is obtained based on the inference result. The network device receives an updated ECN inference model sent by the analysis device.