A automated method for upgrading and/or allocating resources in an IT system for a non-capacity planner (a person unskilled in capacity planning) along with a visual mining technique to aid a capacity planner track down performance degradations is disclosed. The method comprises the steps of collecting a dataset by sampling utilization versus workload of a resource in the IT system and then analyzing said dataset to obtain service time through a new clusterwise regression procedure with a refinement procedure which identifies the (i) cluster memberships, (2) the number of clusters (3) outliers where, said service time being used to trigger the upgrade or allocation of said resources, followed by a visual mining technique to bring out the relationship between the cluster membership and the time stamp Ieading to the identification of sporadic configuration changes which extend over a well defined time frame and the ones composed of isolated recurring observations caused due to scheduled activites.characterized in that the method comprises the following steps divided in two main phases: Phase I : (i) normalize collected dataset, (it) scatter data when utilization has been rounded, (iii) provide for partition of data to find density based dusters through DBSCAIM procedure, (Iv) discard clusters with less than the z% of the total number of observations, (v) in each cluster, perform clusterwise regression and obtain linear sub-dusters in a pre-defined number, (vi) reduce sub-clusters applying refinement procedure, removing sub- dusters that fit to outliers and merging pairs of clusters that fit the same model, (vi) update clusters with the reduced sub-clusters, (vii) remove globular clusters, (viii) reduce number of clusters with refinement procedure, and (ix) de-normalize results. Phase II : Visual minining (i) calculate the silhouette value for each point to measure the strength of point to cluster membership (Si) choose value of threshold (Hi) output the charts - Silhouette-Time Chart, Cardinality-Time Chart, Parameter-Time Chart, Hour of day Chart, Day of week Chart and Timetable Chart for indentifying the bottlenecks.

Automated service time estimation method for IT system resources

CREMONESI, PAOLO;DHYANI, KANIKA
2010

Abstract

A automated method for upgrading and/or allocating resources in an IT system for a non-capacity planner (a person unskilled in capacity planning) along with a visual mining technique to aid a capacity planner track down performance degradations is disclosed. The method comprises the steps of collecting a dataset by sampling utilization versus workload of a resource in the IT system and then analyzing said dataset to obtain service time through a new clusterwise regression procedure with a refinement procedure which identifies the (i) cluster memberships, (2) the number of clusters (3) outliers where, said service time being used to trigger the upgrade or allocation of said resources, followed by a visual mining technique to bring out the relationship between the cluster membership and the time stamp Ieading to the identification of sporadic configuration changes which extend over a well defined time frame and the ones composed of isolated recurring observations caused due to scheduled activites.characterized in that the method comprises the following steps divided in two main phases: Phase I : (i) normalize collected dataset, (it) scatter data when utilization has been rounded, (iii) provide for partition of data to find density based dusters through DBSCAIM procedure, (Iv) discard clusters with less than the z% of the total number of observations, (v) in each cluster, perform clusterwise regression and obtain linear sub-dusters in a pre-defined number, (vi) reduce sub-clusters applying refinement procedure, removing sub- dusters that fit to outliers and merging pairs of clusters that fit the same model, (vi) update clusters with the reduced sub-clusters, (vii) remove globular clusters, (viii) reduce number of clusters with refinement procedure, and (ix) de-normalize results. Phase II : Visual minining (i) calculate the silhouette value for each point to measure the strength of point to cluster membership (Si) choose value of threshold (Hi) output the charts - Silhouette-Time Chart, Cardinality-Time Chart, Parameter-Time Chart, Hour of day Chart, Day of week Chart and Timetable Chart for indentifying the bottlenecks.
File in questo prodotto:
File Dimensione Formato  
id00000016499914.pdf

Accesso riservato

: Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione 3.25 MB
Formato Adobe PDF
3.25 MB Adobe PDF   Visualizza/Apri
US9350627B2.pdf

accesso aperto

: Publisher’s version
Dimensione 1.72 MB
Formato Adobe PDF
1.72 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11311/589896
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact