Conference paper Open Access

An Exposed Closed-Loop Model forCustomer-Driven Service Assurance Automation

Xie, Min; Michelinakis, Foivos; Dreibholz, Thomas; S. Pujol-Roig, Juan; Malacarne, Sara; Majumdar, Sayantini; Yi Poe, Wint; M. Elmokashfi, Ahmed


Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.4707588", 
  "language": "eng", 
  "title": "An Exposed Closed-Loop Model forCustomer-Driven Service Assurance Automation", 
  "issued": {
    "date-parts": [
      [
        2021, 
        4, 
        21
      ]
    ]
  }, 
  "abstract": "<p>This repository accompanies the conference paper with the same title: &quot;An Exposed Closed-Loop Model forCustomer-Driven Service Assurance Automation&quot;, published in EuCNC 2021. In the paper we propose&nbsp;an exposed CL model based on service exposure which is&nbsp;meant&nbsp;to automate service assurance tasks like auto-scaling in a network function virtualization (NFV) system orchestrated by ETSI Open Source MANO (OSM).&nbsp;Here we provide&nbsp;the testbed-generated experimental results we used to validate our proof-of-concept.</p>\n\n<p>Please refer to the conference paper for details about the topology and the scenario of each experiment.</p>\n\n<p>The csv files can be grouped in 3 categories, which correspond to the three vantage points (levels) of monitoring. Each experiment repetition is represented by a hash. The hash is either in the file name or as a column inside the csv files.</p>\n\n<p><strong>1. prometheus.csv</strong></p>\n\n<p>Some of the columns are:</p>\n\n<ul>\n\t<li>timestamp: timestamp in Oslo timezone</li>\n\t<li>experimentHash: the unique identifier of the experiment</li>\n\t<li>vdu_name: Where the data comes from</li>\n\t<li>metric_name: what is being measured</li>\n\t<li>value: the actual value.</li>\n</ul>\n\n<p>It was hard to make this csv&nbsp;flat&nbsp;(ie. use as a unique index the timestamp), because the column names would be very long. The way to use it is to filter per,&nbsp;<em><strong>&lt;experimentHash, vdu_name, metric_name&gt;</strong></em>&nbsp;and then use&nbsp;<em><strong>&lt;timestamp, value&gt;</strong></em>&nbsp;to plot the timeseries of the value for this metric (experimentHash) of this component (vdu_name) for this experiment (experimentHash).</p>\n\n<p><strong>2.&nbsp;sysstat&nbsp;csv</strong></p>\n\n<p>There are 3 csv with the systat values . They contain&nbsp;exactly the same information&nbsp;just in different representations. So, pick the one that is most convenient for you.</p>\n\n<p><strong>3. packet capture csv (csv that starts with a hash)</strong></p>\n\n<p>These are csvs from the packet capture (pcap) files. You can tell by the name which component created them. The files that end with a number are captured at the client (UE). Refer to the topology figure of the conference publication.</p>", 
  "author": [
    {
      "family": "Xie, Min"
    }, 
    {
      "family": "Michelinakis, Foivos"
    }, 
    {
      "family": "Dreibholz, Thomas"
    }, 
    {
      "family": "S. Pujol-Roig, Juan"
    }, 
    {
      "family": "Malacarne, Sara"
    }, 
    {
      "family": "Majumdar, Sayantini"
    }, 
    {
      "family": "Yi Poe, Wint"
    }, 
    {
      "family": "M. Elmokashfi, Ahmed"
    }
  ], 
  "id": "4707588", 
  "event-place": "Porto, Portugal", 
  "type": "paper-conference", 
  "event": "European Conference on Networks and Communications (EuCNC)"
}
86
14
views
downloads
All versions This version
Views 8686
Downloads 1414
Data volume 1.9 GB1.9 GB
Unique views 7575
Unique downloads 44

Share

Cite as