Network Congestion Control with Egress Bandwidth and Flow Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional congestion control methods in communication networks fail to accurately reflect network status, leading to ineffective congestion management.
Innovation Solution
Determine the sending rate of data flows based on the total bandwidth and quantity of active flows or sending devices at the egress port of a network device, using a formula that positively relates the rate to bandwidth and negatively relates it to the number of active flows or devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the sending rate is determined based only on the receiving device status and bandwidth usage of ingress port, then the congestion control method is simple, but the network status cannot be accurately reflected leading to poor congestion control effect
Solution Approach 1:
The patent implements feedback by having the network device send congestion control information (bandwidth and active flow quantity) back to the sending device. The sending device then adjusts the sending rate based on this feedback, creating a closed-loop control system that accurately reflects network status and improves congestion control effectiveness.
Solution Approach 2:
The network device acts as an intermediary between the sending device and receiving device. It collects status information from the receiving device, processes it by determining bandwidth and active flow quantity, and sends this processed information to the sending device for rate determination, thereby improving measurement precision without requiring the sending device to directly monitor network status.
2Reliability
If the sending rate is determined based on total bandwidth and quantity of active flows, then the congestion control effect is improved, but the information processing complexity increases
Solution Approach 1:
The patent segments the congestion control information into distinct components: total bandwidth of the egress port and quantity of active flows. This segmentation allows the sending device to process each parameter separately and apply them systematically in the sending rate determination formula, reducing processing complexity while maintaining reliability.
Solution Approach 2:
The patent changes the parameters used for congestion control from simple bandwidth usage to a combination of total bandwidth and quantity of active flows. This parameter change improves congestion control effectiveness by providing a more comprehensive view of network status, while the standardized formula for rate determination keeps processing complexity manageable.
3Productivity
If the sending rate is positively related to total bandwidth and negatively related to quantity of active flows, then the bandwidth utilization is optimized, but the calculation complexity increases
Solution Approach 1:
The sending device performs self-service by autonomously determining its sending rate based on the received congestion control information and the predefined relationship (positively related to bandwidth, negatively related to active flows). This self-service approach optimizes bandwidth utilization without requiring complex centralized control, as each sending device independently adjusts its rate according to network conditions.
Data Source
AI summary
A method for implementing congestion control includes: obtaining congestion control information of a first network device, where the congestion control information includes a total bandwidth of a first egress port of the first network device and a quantity of active flows corresponding to a first queue of the first egress port; and determining a sending rate of a first data flow in the active flows based on the congestion control information, where the sending rate is positively related to the total bandwidth and negatively related to the quantity of active flows, and the sending rate is used by a sending device of the first data flow to send the first data flow.