One-way packet delay is an important network performance metric. Recently, a new data structure called Lossy Difference Aggregator (LDA) has been proposed to estimate this metric more efficiently than with the classical approaches of sending individual packet timestamps or probe traffic. This work presents an independent validation of the LDA algorithm and provides an improved analysis that results in a 20% increase in the number of packet delay samples collected by the algorithm. We also extend the analysis by relating the number of collected samples to the accuracy of the LDA and provide additional insight on how to parametrize it. Finally, we extend the algorithm to overcome some of its practical limitations and validate our analysis using real network traffic.
展开▼
