Peering Link Traffic Regulation via Retransmission Rate Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In networks, peering links often face capacity issues due to underprovisioning, leading to performance degradation such as re-buffering during video streaming, as existing methods struggle to effectively regulate traffic on these links.
Innovation Solution
A system that determines and compares retransmission rates of data packets across different time intervals to adjust the target acceptance rate for requests to initiate conversations via peering links, accepting or rejecting requests based on the actual vs. target acceptance rate to maintain communication performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If peering links are underprovisioned to reduce costs, then capital expenditure is reduced, but traffic regulation capability deteriorates leading to overflow conditions
Solution Approach 1:
The system performs preliminary actions by determining the acceptance rate before overflow occurs, using historical retransmission rates and current retransmission rates to predict link capacity needs. This allows the system to proactively regulate traffic acceptance rather than reactively responding to overflow conditions, thereby maintaining reliability with underprovisioned links
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring retransmission rates and using this information to adjust the acceptance rate dynamically. The comparison between historical retransmission rates and current retransmission rates creates a closed-loop control system that adapts to changing traffic conditions, enabling effective traffic regulation despite limited link capacity
2Productivity
If acceptance rate is increased to maximize link utilization, then productivity improves, but performance degradation increases due to overflow conditions
Solution Approach 1:
The system applies dynamics by making the acceptance rate adjustable and adaptive rather than fixed. The acceptance rate changes dynamically based on the comparison between historical retransmission rates and current retransmission rates, allowing the system to optimize link utilization while preventing performance degradation through real-time adaptation to traffic conditions
Solution Approach 2:
The system changes parameters by adjusting the acceptance rate based on retransmission rate comparisons. When current retransmission rates indicate approaching capacity limits, the acceptance rate is reduced to prevent overflow. This parameter adjustment mechanism enables the system to maintain high link utilization while avoiding the performance degradation that would result from static high acceptance rates
Data Source
AI summary
A system which regulates communication with a server is described. During operation, the system determines a retransmission rate of data packets during a first set of conversations between a group of users and the server via a peering link. Next, the system compares the retransmission rate and an historical retransmission rate of data packets during a second set of conversations between a second group of users and the server via the peering link. The system then adjusts a target acceptance rate of the server to requests to initiate conversations with additional users via the peering link based on the comparison of the retransmission rate and the historical retransmission rate. Additionally, the system accepts or rejects a request to initiate a conversation between another user and the server via the peering link based on an actual acceptance rate of the server to requests to initiate the conversations and the target acceptance rate.