Latency-Based Random Early Discard for Network Packet Queues
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network systems face challenges in managing packet queues effectively during overload conditions, primarily focusing on memory usage rather than end-user experience, leading to inefficient packet discard decisions.
Innovation Solution
Implementing a latency-based random early discard mechanism that identifies and prioritizes packet queues based on latency metrics, such as average or median latency, to determine which packets should be discarded, thereby focusing on end-user experience while also considering system resource preservation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If WRED mechanisms use memory usage thresholds to determine packet discard, then system resource preservation is improved, but end-user experience deteriorates
Solution Approach 1:
The patent changes the parameter basis for packet discard decisions from memory usage (buffer occupancy) to latency-based metrics. Specifically, it uses time-based metrics such as average latency, median latency, or latency percentiles to trigger Random Early Discard (RED) actions. This parameter change allows the system to preserve resources while maintaining better end-user experience by focusing on actual packet delay rather than abstract buffer levels.
Solution Approach 2:
The patent implements feedback mechanisms that continuously monitor latency metrics and adjust packet discard decisions accordingly. The system measures latency for packets in different queues, compares these measurements against thresholds, and dynamically adjusts discard probabilities based on the observed latency patterns. This closed-loop feedback ensures that discard actions are taken based on actual performance impact to user experience.
2Reliability
If latency-based discard is implemented, then end-user experience is improved, but device complexity increases
Solution Approach 1:
The patent segments the queue management system into distinct functional components: latency measurement modules that track time-based metrics for different queues, threshold comparison modules that evaluate measured latencies against configured thresholds, and packet discard modules that execute RED decisions. This segmentation allows each component to perform a specific function, making the overall complex system more manageable and maintainable while still achieving improved end-user experience.
Data Source
AI summary
Methods, systems, and apparatus used to determine whether to discard a network packet based upon the latency exhibited by an associated a network packet queue. Network devices can include a queue management module operable to identify a latency metric in network packet queues and determine whether the latency metric renders the network packet queue eligible for discarding packets based upon, for example, a latency policy.