Master thesis with focus on machine learning for temperature handling
We are looking for a Master thesis student to investigate how machine learning methods can be used for smart temperature handling in our radio products.
There is an industry trend in favor of small radio products, making them easy to deploy while reducing the required tower or installation space. Consequently, keeping functioning temperature levels in our radio equipment becomes increasingly challenging.
In hot weather environments and for certain installation scenarios, it may also happen that our equipment is perceived as lacking the temperature robustness it has been designed for.
We believe that by predicting the weather and temperature behavior we will be able to take suitable and timely actions to keep the product in operation and the network service in the best possible shape.
The purpose of the thesis is to propose a learning algorithm(s) with the aim of optimizing the network capacity and user experience in hot weather conditions without risking that the radio equipment shuts down.
- Performance over a temperature cycle (day or week)
- Radio unit temperature sensors profile vs. traffic profile during a temperature cycle
- Data exists and can be manipulated with offsets
- Learning algorithms to improve the radio performance in hot weather: based on the analysis of the input data, suggestion on actions to be taken.
- Smarter algorithms for our test environments (replacing environment chamber tests with input loops in a normal environment – i.e. cooling commands used in a controlled way).
- Machine learning based control mechanisms. Choosing an appropriate machine learning method and programming environment are part of the assignment.
- Simulations and evaluations of traffic and temperature models during a temperature defined cycle (day or week).
- Real case trial on a customer site, if possible.
Details will be agreed and regularly reviewed with your Ericsson thesis supervisor.
You will be working in the Ericsson Kista office, starting in January 2019 for a duration of 6 months.
- Master of Science student in computer science, data analytics or similar
- Experience running simulations for performance estimation
- A background in physics, mechanical engineering or control theory is a plus
- Good communication skills
- Fluent in English
Please include your grades together with your application.
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: 263041