Skip to content
Dataset used for IFIP Networking 2019
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.
dataset First commit May 9, 2019

DeepMPLS: Fast Analysis of MPLS Configurations Using Deep Learning

This repository contains the dataset used for the paper "DeepMPLS: Fast Analysis of MPLS Configurations Using Deep Learning" publish at the IFIP Networking 2019 conference. We refer to the paper for a full explanation of the methodology used for generating the dataset.

Reading the dataset

This dataset is based on the networks from the topology-zoo dataset. The repository contains two types of files:

  • Network description files, stored as a tar.gz archive, containing the topologies and the MPLS rules in XML format. The XML format can be processed using P-Rex.
  • Queries files in compressed JSON format.

The matching between network descriptions and queries files is done via the filenames (see example below).

The dataset/qpred folder corresponds to the Satisfiability and Routing tasks in the paper, and the dataset/cpred folder corresponds to the Partial synthesis task.

Example query in the JSON files

In dataset/cpred/topology-zoo/Arpanet196912.queries.json.gz, the first query is:

  "query": "<11> SRI .* UCLA <> 0",
  "query_result": true,
  "network": "s1p49"

This query corresponds to the network described by the s1p49/topo.xml and s1p49/routing.xml files from the archive dataset/cpred/topology-zoo/Arpanet196912.xmls.tgz.


If you use this dataset for your research, please include the following reference in any resulting publication:

	author    = {Geyer, Fabien and Schmid, Stefan},
	title     = {{DeepMPLS}: Fast Analysis of MPLS Configurations Using Deep Learning},
	booktitle = {Proceedings of the 18th IFIP Networking Conference},
	year      = {2019},
	month     = mai,
	address   = {Warsaw, Poland},
You can’t perform that action at this time.