Ericsson Master Thesis - Reinforcement learning applied on NFV architecture, JS4 in Stockholm, Sweden

Master Thesis – Reinforcement learning applied on NFV architecture

Fueled by the technical promises that comes with virtualization and cloud deployment techniques, our industry is going through a fundamental change in terms of how products and services are being developed, tested, delivered, deployed and “signed off” between vendors and customers. Automated service orchestration, machine learning and analytics driven decision making are all driving concepts in this exciting transformation journey.

In the industry engagement around Network Function Virtualization (NFV), cloud technology and service orchestration are taken to the context of a full communication system. With NFV, entire classes of traditional network node functions can be virtualized into building blocks that chain together to create communication services, hosted in the cloud and consumed as a service.

Ericsson is in the lead of this transformation and we develop technologies and services leading towards pioneering new ways to connect systems, cities, and societies in ways we never thought possible. We envision that future communication systems will be self-learning, automated, proactive and without manual intervention, throughout the entire lifecycle of supported products and services.

We offer you the possibility to join us in the journey towards the Networked Society!

Your assignment:

The objective of the thesis is to investigate solutions for applying Reinforcement Learning (an area of Machine Learning) on Virtual Network Functions (VNFs) residing on an NFV Infrastructure (NFVi), to enable use-cases for autonomous lifecycle management of the architecture. For instance self-adopting mechanisms for scaling in/out the applications depending on the fluctuations of traffic in the network.

The assignment will be a combination of studies, design and concrete prototyping. It is expected that at the end of the assignment, besides a final thesis report, you will be able to live demonstrate your findings to stakeholders in terms of a prototype.

As the area of Machine Learning in the context of communication services in cloud and NFV is a broad area with many possible approaches, the assignment can either be done as individual or as a team of two students with slightly different angles of incidence. Expected starting date is preferably during fall of 2017.


As a person, you want to perform at your best and you want to participate in deep technical discussions with other team members. You believe that disruptive innovation happens in the intersection of different technology areas. We are looking for a self-motivated and creative student(s) with the following qualifications;

  • You are close to finalizing your studies in Electrical Engineering, Computer Science or related areas
  • You like to work in an environment where you co-operate closely with your team colleagues, together striving to fulfill common targets.
  • You like to communicate with people and find it easy to explain your findings and knowledge to others.
  • You have very strong analytical skills and are eager to find innovative solutions to problems.
  • You have knowledge and experience from areas such as machine learning, neural networks, data driven sw-development
  • You are comfortable in Linux environments and hands-on in building and getting up to speed in your own prototyping sandbox environment by selecting and integrating necessary open source component as needed
  • You should have a sound understanding of digital communications, wireless systems design and strong programming skills.
  • Fluency in English


The selection process is ongoing and planned start of the thesis would preferably be in the time-frame of October 2017.

Why is Ericsson a great place to work?

Ericsson is the driving force behind the Networked Society where every person and every industry is empowered to reach their full potential. Mobility, broadband and the cloud are transforming the world, enabling industries and society to provide better services, capture new opportunities, improve businesses, increase efficiency, and create new user experiences.

Our services, software and infrastructure support every major telecom operator in the world. The transformation that this brings allows people, business and society to fulfill their potential and build a more sustainable future.

With some 115,000 employees and customers in 180 countries, we combine global scale with technology and services leadership. We support networks that connect more than 2.5 billion subscribers. 40 percent of the world’s mobile traffic is carried over Ericsson networks. And our SEK 100 billion investment in research and development over the last three years ensure that our solutions – and our customers – are at the forefront of innovation.

At Ericsson, we give our employees the freedom to think big. Your ideas and innovations can turn into achievements that impact society and change the world. Are you ready to be a change-maker? Learn what makes YOU + Ericsson a powerful combination. Join us today.

Founded in 1876, Ericsson has its headquarters in Stockholm, Sweden. Net sales in 2014 were SEK 228.0 billion (USD 33.1 billion). Ericsson is listed on NASDAQ OMX stock exchange in Stockholm and the NASDAQ in New York.

Ericsson provides equal employment opportunities (EEO) to all employees and applicants for employment without regard to race, color, religion, sex, sexual orientation, marital status, pregnancy, parental status, national origin, ethnic background, age, disability, political opinion, social status, veteran status, union membership or genetics.

Ericsson complies with applicable country, state and all local laws governing nondiscrimination in employment in every location across the world in which the company has facilities. In addition, Ericsson supports the UN Guiding Principles for Business and Human Rights and the United Nations Global Compact.

This policy applies to all terms and conditions of employment, including recruiting, hiring, placement, promotion, termination, layoff, recall, transfer, leaves of absence, compensation, training and development.

Ericsson expressly prohibits any form of workplace harassment based on race, color, religion, sex, sexual orientation, marital status, pregnancy, parental status, national origin, ethnic background, age, disability, political opinion, social status, veteran status, union membership or genetic information.

Primary country and city: Sweden (SE) || No Selection || Stockholm || Stud&YP;

Req ID: 204943