Traffic Policing Detection Using Passive Rate Limit Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing traffic policing strategies face challenges in accurately estimating rate limits during traffic bursts, leading to packet loss and reduced Quality of Experience (QoE) due to inaccurate detection of traffic policing, especially in networks with multiple intermediate nodes and random loss factors, and active detection methods increase network overhead.
Innovation Solution
A passive traffic policing detection method using sampled packet loss rates and acknowledgement rates to determine a correlation coefficient, distinguishing between traffic policing and random loss through linear fitting, enabling accurate estimation of rate limits without additional network traffic.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If active detection methods are used to detect traffic policing, then detection accuracy is improved, but network overhead increases
Solution Approach 1:
The system uses existing packet transmission and acknowledgment mechanisms to detect traffic policing. The sending device monitors its own transmitted packets and received acknowledgments to calculate loss rates and detect policing, eliminating the need for separate detection traffic.
Solution Approach 2:
The packet loss detection mechanism serves multiple functions: it detects traffic policing, estimates rate limits, and provides feedback for congestion control. This multi-functionality eliminates the need for dedicated detection mechanisms, reducing network overhead.
2Device complexity
If traffic policing is implemented with fixed token bucket capacity, then flow control is simplified, but accuracy in rate limit estimation deteriorates during traffic bursts
Solution Approach 1:
The system dynamically adjusts the token bucket capacity based on detected traffic patterns and calculated rate limits. Instead of using a fixed capacity, the capacity is adapted to match actual network conditions and policing behavior, improving estimation accuracy during traffic bursts.
Solution Approach 2:
The system continuously monitors packet loss rates and acknowledgment patterns to calculate rate limits, then feeds this information back to adjust the token bucket capacity. This closed-loop feedback mechanism maintains accurate rate limit estimation under varying traffic conditions.
3Measurement precision
If packet sampling is performed to detect traffic policing, then detection precision is improved, but processing complexity increases
Solution Approach 1:
Instead of analyzing every packet, the system samples a subset of packets to estimate loss rates and detect traffic policing. This partial action approach maintains detection precision while significantly reducing processing complexity compared to full packet analysis.
Data Source
AI summary
Apparatus, method and non-transitory computer readable medium for traffic policing detection and rate limit estimation for a network, including selecting from the network sampled packets having a loss rate greater than a first threshold, the selected sampled packets being added to a sliding window for traffic policing detection; in response to the number of sampled packets in the sliding window reaching a predetermined number, determining a correlation coefficient based on a sending rate and the loss rate of at least one sampled packet in the sliding window; in response to the correlation coefficient exceeding a second threshold, determining whether traffic policing is occurring in the network based on the sending rate and a transformed loss rate of the at least one sampled packet; and in response to traffic policing occurring, determining an estimated rate limit for traffic policing based on an acknowledgement rate of the at least one sampled packet.