PDF - Automating Data Center Operation using Machine Intelligence - QC-118

Preferred Disciplines: Computer Engineering, Post-Doc Fellow
Company: Ericsson Canada Inc
Project Length: 1 PDF for 2 yrs
Desired start date: ASAP
Location: St Laurent, Quebec
No. of Positions: 1
Preferences: The candidate should be curious, ready to learn, passionate in the area of Machine Intelligence. The candidate should also be autonomous to a certain degree, ready to deliver results as needed. It is understood that there will be a learning curve to align with Ericsson.

About Company:

Ericsson as a major international telecom operator, and one of the top ten R&D investors in Canada, is both cloud service provider and cloud user. As a cloud service provider, investing over a billion dollars in building a massive ICT R&D center in Quebec, it is very important for Ericsson to have contingency plans for Disaster Recovery in place. Ericsson has also demonstrated its corporate responsibility for energy efficient and green solutions based on a long history of research in energy consumption and Life Cycle Assessment (LCA).

Project Description:

Manual performance, configuration and fault management of Data Centers is vunerable to human intervention and therefore subject to human errors. One way to circumvent this problem is to use Machine Intelligence in order to automate some of the Data Center operations which already benefit from expert knowledge.

The Research Area will be devoted to one or more of these themes:

Machine Intelligence for automation of Data Center operation,
Machine Intelligence for automation of Data Center maintenance and/or
Machine Intelligence for automation of Data Center upgrades of containerized Micro-Services.

Although 3 themes are listed above, the Automation of Data Center upgrades of containerized Micro-Services (3) is the main area sought after.

Background and required skills

Research Objectives/Sub-Objectives:

Provide Machine Intelligence for automation of Data Center.

Operation which refers to the automation of Configuration, Resource and Performance Management.
Maintenance or fault avoidance/prevention.

  • Upgrades of containerized Micro-Services.

Methodology:

The methodology will be focused on:

  • State of the art of current deployment, continuous delivery of micro-services in fully connected containers
  • What is the next step to reduce Human intervention within 2 years?
  • What can bring us to full automation of deployment, continuous delivery of micro-services in fully connected containers? This item would result in providing us with a migration plan towards automation?

Expertise and Skills Needed:

  • Preferably, good understanding of Machine Learning
  • If possible, good understanding of Deep Learning
  • If possible, good understanding of Re-enforcement Learning

For more info or to apply to this applied research position, please

  1. Check your eligibility and find more information about open projects.
  2. Complete this webform. You will be asked to upload your CV. Remember to indicate the title of the project(s) you are interested in and obtain your professor’s approval to proceed!
  3. Interested students need to get the approval from their supervisor and send their CV along with a link to their supervisor’s university webpage by applying through the webform or directly to Jesse Vincent-Herscovici  at, jvh(a)mitacs.ca

Program: