Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Finding a "Kneedle" in a Haystack: Detecting Knee Points in System Behavior

Summary: Finding a "Kneedle" in a Haystack:
Detecting Knee Points in System Behavior
Ville Satopšaša, Jeannie Albrecht, David Irwin, and Barath Raghavan§
Williams College, Williamstown, MA
University of Massachusetts Amherst, Amherst, MA
§International Computer Science Institute, Berkeley, CA
Abstract--Computer systems often reach a point at which the
relative cost to increase some tunable parameter is no longer
worth the corresponding performance benefit. These "knees" typ-
ically represent beneficial points that system designers have long
selected to best balance inherent trade-offs. While prior work
largely uses ad hoc, system-specific approaches to detect knees,
we present Kneedle, a general approach to online and offline
knee detection that is applicable to a wide range of systems.
We define a knee formally for continuous functions using the
mathematical concept of curvature and compare our definition
against alternatives. We then evaluate Kneedle's accuracy against
existing algorithms on both synthetic and real data sets, and
evaluate its performance in two different applications.


Source: Albrecht, Jeannie - Computer Science Department, Williams College
Massachusetts at Amherst, University of - Architecture and Language Implementation
Shenoy, Prashant - Department of Computer Science, University of Massachusetts at Amherst


Collections: Computer Technologies and Information Sciences