Output details
11 - Computer Science and Informatics
University of Edinburgh
Fine-grained latency and loss measurements in the presence of reordering
<06> Originality: Presents a novel data structure that detects problematic packet reordering, mitigates its impact, and improves accuracy in end-to-end network latency and loss measurements.
Significance: The proposed data structure obtains 10 times more accurate latency estimates and achieves 200 times lower errors for loss measurements compared to the state-of-the-art solution proposed so far.
Rigour: Effectiveness and parameter configuration of our data structure is formally studied via proofs and experiments. Published in ACM SIGMETRICS 2011, one of the premier computer systems performance evaluation conferences, with only a 14.7% acceptance rate.