04.01.16 - 07.01.16, Seminar 16012

Global Measurements: Practice and Experience

The following text appeared on our web pages prior to the seminar, and was included as part of the invitation.


Several large-scale Internet measurement systems have been deployed during the last years in order to understand how the network is performing, to observe how it is evolving, and to determine where failures or degradations occur. Large-scale measurements are meanwhile used to drive network operations and to dynamically adjust how services are delivered to customers. One key challenge is that global Internet measurement systems can generate large amounts of data that need to be processed to derive relevant information.

This Dagstuhl Seminar is a follow-up of Dagstuhl Seminar 13472 “Global Measurement Frameworks” that took place in November 2013. It aims at discussing the practical experience gained with global measurement frameworks and it will look at the experience gained with metrics, data processing technologies, and data analysis methods. Starting from these three dimensions, the seminar aims to discuss the following key questions:

Measurement Metrics

  • Which metrics have been found useful for measuring quality of experience of certain classes of services?
  • Which metrics have been found problematic?
  • Is it possible to find indicators for good metrics and problematic metrics?
  • Is it possible to formulate guidelines for the development of robust metrics?

Data Processing Technologies

  • Which technologies have been found useful for storing and processing large amounts of measurement data?
  • Which technologies were found to be problematic?
  • Are there new promising technologies being developed that may be used in the future?
  • What are the specific requirements for dealing with global measurement data and how do they relate to or differ from other big data applications?

Data Analysis Methods

  • Which data analysis techniques have been found useful?
  • Which data analysis techniques have been found problematic?
  • Are there any novel promising techniques that need further research and development?