Software — Stack — for Massively Geo-Distributed Infrastructures

logo IMT Atlantique logo inria logo LS2N

Research Internship (Master 2) on Decision models for Edge-Cloud systems -

Global information


Start: March 1st, 2024
Duration: 6 months
Supervision: Daniel Balouek, IMT Atlantique & Inria team STACK, daniel.balouek@inria.fr
Keywords: Edge-to-Cloud continuum; Urgent Computing; Event-driven systems; Resource Management
Link to the offer

Context


This internship focuses on decision support for the management on resources distributed across the Edge-Cloud Computing continuum. The location (which physical server) and the execution parameters (which software configuration) have significant effect on the performance of applications. Particularly, emerging data-driven applications are built as compositions of individual functions deployed between the edge of the network (where data is produced from physical/virtual sensors) and the cloud (where final data-processing steps are usually performed). Each function consists in stand-by code with input parameters depending on the previous step and the overall performance expected by the developers. Managing the application as a whole requires decision mechanisms to perform the placement of individual functions through uncertainty and constraints by identify runtime events, and trigger appropriate policies

Expected Work


In this context, the successful candidate will be in charge of proposing and evaluating a decision model. The main challenge consists in modeling the different outcomes of the system, and deducing management policies based on their impact. The objectives of this internship are :

  • a state-of-the-art to assess the concepts associated to the computing continuum and data-driven analytics
  • proposing a mathematical model integrating the status, events and performance metrics of a system deployed across edge and cloud resources
  • evaluating the model on a real-platform using an urgent application

Skills


The following skills are expected from the successful candidate :

  • a student in the last year of a Master’s degree in Computer Science (or in the last year of an engineering school with a computer science option) ;
  • modeling skills to be able to abstract the properties of the computing continuum and the urgent applications ;
  • knowledge of the Python programming language ;
  • basics in probability and statistics ;
  • a good level of English to contribute to the writing of a research paper ;
  • an ability to collaborate and communicate ;
  • curiosity and an appetite for learning new things.

More details here