Master Thesis - Machine Learning based 5G Drone Route Planning i Stockholm, Sweden

Background

Machine learning constitutes a set of algorithms that can learn from and make predictions on data. Such algorithms operate by building a model from inputs to make predictions or decisions, rather than following strictly static program instructions. These set of algorithms have successfully been applied to various applications such as computer security, bioinformatics, computer vision, medical diagnosis, and search engines. Common to all these fields is the need to automatically process large set of data to generate useful insights and take appropriate decisions.

Mobile networks are complex by nature. A 4G (LTE) network today is by far more complex compared to a 2G (GSM) network due to increasing number of base stations and users, but also due to advancements in radio and network technology. In addition, it is expected that the next-generation, 5G, mobile communication systems will handle an even broader set of scenarios, not fully addressed by current cellular systems. This includes massive deployment of ultra-low power sensors, intelligent traffic systems, critical low-latency communications, enterprise networks, etc.

To handle this complexity there is a need to deploy intelligent methods for analyzing data from 4G and 5G networks. Such methods need to reduce efforts for network management (essentially offloading human effort needed to operate the networks), can draw new insights, and predict future network and user behavior to make smarter decisions. This could result in higher network performance, better reliability, and more adaptive systems.

In recent years, the use of flying drones have increased, and today it is not uncommon for them to be equipped with cameras, in order to provide a video feed from the drone. The drones are typically controlled via a propiratary protocol limiting the flying distance to a few kilometers. By instead connecting the drone via LTE (control and video feed), the distance between user and drone can be dramatically extended. However, from a network perspective, such drones can cause disturbances in network performance due to the heavy interference induced by such telecom traffic. In order to reduce this interference, one would like to plan the drone routes, which in this thesis involves the use of reinforcement learning.

Thesis Description

This thesis work will investigate machine learning methods to plan drone routes in 5G networks. This involves collecting, extracting and analyzing data in order to create a data-driven drone route planning tool. The data collection can comprise both of network simulations, and real measurements from a flying .

Qualifications

This project aims at students in electrical engineering, computer science, computer engineering, machine learning or similar. The student should have the following qualifications:

• Programming skills in Java, Python
• Hands on experience with ML libraries like numpy, pytorch, tensorflow
• Very good knowledge about Reinforcement Learning
• Innovative and creative thinking
• English written and spoken

Extent

1 student, 30hp

Location

Ericsson AB, Kista (Stockholm), Sweden

Preferred Starting Date

Spring 2019

Keywords

Machine Learning, Reinforcement Learning, Drones

Recruitment Specialist: Sylwia Kwiecień

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) || || Stockholm || Stud&YP

Req ID: 257460