Using Search Methods for Selecting and Combining Software Sensors to Improve Fault Detection in Autonomic Systems

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

@InProceedings{Shevertalov:2010:SSBSE,
  author =       "Maxim Shevertalov and Kevin Lynch and 
                 Edward Stehle and Chris Rorres and Spiros Mancoridis",
  title =        "Using Search Methods for Selecting and Combining
                 Software Sensors to Improve Fault Detection in
                 Autonomic Systems",
  booktitle =    "Second International Symposium on Search Based
                 Software Engineering (SSBSE 2010)",
  year =         "2010",
  month =        "7-9 " # sep,
  pages =        "120--129",
  isbn13 =       "978-1-4244-8341-9",
  keywords =     "genetic algorithms, genetic programming, autonomic
                 system, convex-hull geometric object, fault detection,
                 genetic-algorithm, genetic-programming,
                 multidimensional space, random-search approach, search
                 method, software sensor, fault tolerant computing,
                 search problems",
  DOI =          "doi:10.1109/SSBSE.2010.23",
  abstract =     "Fault-detection approaches in autonomic systems
                 typically rely on runtime software sensors to compute
                 metrics for CPU load, memory usage, network throughput,
                 and so on. One detection approach uses data collected
                 by the run time sensors to construct a convex-hull
                 geometric object whose interior represents the normal
                 execution of the monitored application. The approach
                 detects faults by classifying the current application
                 state as being either inside or outside of the convex
                 hull. However, due to the computational complexity of
                 creating a convex hull in multi-dimensional space, the
                 convex-hull approach is limited to a few metrics.
                 Therefore, not all sensors can be used to detect faults
                 and so some must be dropped or combined with
                 others.

                 This paper compares the effectiveness of
                 genetic-programming, genetic-algorithm, and
                 random-search approaches in solving the problem of
                 selecting sensors and combining them into metrics.
                 These techniques are used to find 8 metrics that are
                 derived from a set of 21 available sensors. The metrics
                 are used to detect faults during the execution of a
                 Java-based HTTP web server. The results of the search
                 techniques are compared to two hand-crafted solutions
                 specified by experts.",
  notes =        "grammar with five(three) rules. NanoHTTPD Java Ruby
                 SSH QHull. 'many good solutions exist in the space
                 being searched'. 'We expect the difference between the
                 quality of human and computer-generated solutions to
                 increase as more sophisticated applications begin using
                 this technique.'

                 IEEE Computer Society Order Number P4195 BMS Part
                 Number: CFP1099G-PRT Library of Congress Number
                 2010933544 http://ssbse.org/2010/program.php Also known
                 as \cite{5635154}",
}

Genetic Programming entries for Maxim Shevertalov Kevin Lynch Edward Stehle Chris Rorres Spiros Mancoridis

Citations