Dave Taht
2018-06-18 20:53:54 UTC
while I'm finishing catching up on current research, vesper looked
good, especially in
its analysis of how various various methods are for calculating PLT.
"The surprising aspect of the results is that the differences between
the metrics are so noticeable. As shown in Figures 2(a) and 3, the
differences are large in terms of percentage (24.0%–64.3%); more
importantly, the differences are large in terms of absolute magnitude,
equating to hundreds or thousands of milliseconds"
http://web.mit.edu/ravinet/vesper_nsdi18.pdf
good, especially in
its analysis of how various various methods are for calculating PLT.
"The surprising aspect of the results is that the differences between
the metrics are so noticeable. As shown in Figures 2(a) and 3, the
differences are large in terms of percentage (24.0%–64.3%); more
importantly, the differences are large in terms of absolute magnitude,
equating to hundreds or thousands of milliseconds"
http://web.mit.edu/ravinet/vesper_nsdi18.pdf
--
Dave Täht
CEO, TekLibre, LLC
http://www.teklibre.com
Tel: 1-669-226-2619
Dave Täht
CEO, TekLibre, LLC
http://www.teklibre.com
Tel: 1-669-226-2619