Page 39 - Big data - Concept and application for telecommunications
P. 39

Big data - Concept and application for telecommunications                       1


                                      Table II.2 – Virtualized distributed cluster service

             Title                 Virtualized distributed cluster service
             Description           A virtual distributed cluster service is a typical web service which makes it easy to have a
                                   cluster of machines quickly and cost-effectively processing vast amounts of data provided
                                   by a CSP.
                                   The virtual distributed cluster service uses distributed clustering software as a framework,
                                   to  distribute  the  customers'  data  and  processing  across  a  resizable  cluster  of  virtual
                                   machine instances in cloud resource pools. Three steps that are often included by the CSC
                                   using a virtual cluster service are:
                                   1)  Upload data. The CSC:BDSU uploads the data that needs to be analysed to the cloud
                                      storage space that belongs to the CSC:BDSU. In addition the CSC:BDSU could use the
                                      data provided by the CSN:DP.
                                   2)  Create  virtual  distributed  cluster.  The  CSC:BDSU  creates  and  configures  the
                                      distributed cluster by specifying data inputs, outputs, cluster size, security settings and
                                      other necessary parameters.
                                   3)  Monitor and collect. CSC:BDSU monitors the health and progress of the distributed
                                      cluster using the tools provided by the CSP. When the distributed processing job is
                                      completed the CSC:BDSU retrieves the output in the specified storage space.
                                   A virtual distributed cluster service could be used in a variety of applications, including log
                                   analysis, web indexing, data warehousing, machine learning, financial analysis, scientific
                                   simulation and bioinformatics.
             Roles/Sub-roles       –  CSN:DP
                                   –  CSP:BDAP
                                   –  CSP:BDIP
                                   –  CSC:BDSU
             Figure















































                                                                                    Basics of Big data     31
   34   35   36   37   38   39   40   41   42   43   44