Do you want to do your Master Thesis here with us in Kista?
Come and start your professional journey at Ericsson.
Would you like to take the chance to work in one of the world’s leading technology companies? We are on a quest to enable communication for everyone and everything and we do that by being driven by innovation. If you want to help us to be even more innovative - You are on the right track!
Become a part of a truly global company working across borders in 180 countries, offering a diverse, performance-driven culture & an innovative & engaging environment where employees enhance their potential every day. Learn and grow within Ericsson, to reach your career goals.
Are you driven by innovation? At Ericsson, we apply our innovation to market-based solutions that empower people & society to help shape a more sustainable world.
The IMS (IP Multimedia Subsystem) is part of the 3GPP Reference Network Architecture meant to provide multimedia services over any IP network. Nowadays, IMS is widely deployed to provide Voice over LTE (VoLTE), SMS and Fixed broadband telephony services. Services can also be enhanced by providing Multi-X and RCS. IMS is also providing Voice services over 5G (VoNR).
Before deploying/instantiating IMS network functions on specific cloud environments to provide the aforementioned services, a dimensioning process is conducted in order to estimate, based on the user traffic model of its served subscribers, how many resources (in the form of CPU Load or Memory) will the IMS network functions require from the cloud environment in order to serve those subscribers accordingly. In other words, dimensioning is the process of predicting how much CPU Load and Memory would be required.
This scientific investigation aims to understand how to optimally use Machine Learning to perform dimensioning of IMS network functions, with the main goal of generating generic ML based trained estimators, on the Ericsson’s Machine Learning Execution Environment (MXE) for the different IMS network functions (e.g. SBG, CSCF, MTAS), with the highest accuracy possible as prioritized criterion for ranking of the estimators during inference.
- Evaluate all possible IMS network functions counters to use as inputs/features, to build an appropriate view of each feature influence on the labels to predict (CPU Load and Memory Utilization).
- Investigate around previous work done around using Machine Learning for Dimensioning, and describe their achievements and pitfalls to better approach the scientific investigation.
- Investigate around Ericsson’s strategy on AI, ML and Data Analytics, as well as the Machine Learning Execution Environment (MXE) as the main enabler to execute the ML part of this strategy.
- Investigate around what Performance Management (PM) counters are, and how they can be used as data sources to create the data sets needed for the Data Science work of the investigation.
- Investigate the importance of accurate dimensioning of IMS applications, both for Ericsson as a telecommunications equipment and services provider, and for operators as consumer services provider.
- Investigate around the IP Multimedia Subsystem (IMS) applications in the telecommunications industry, and all the services it provides to consumers.
- Perform detailed data science work around to determine what ML algorithms are optimal to address the scientific work:
- Evaluate and deploy, by using the Ericsson Machine Learning Execution Environment, the ML estimators not only based on accuracy, but also on inference latency, required computation power during training and inference, among others.
- Perform a benchmarking of ML estimators, from simpler ones to complex ones (using many different estimators like simple linear regression, probabilistic estimators like Naive Bayes, biologically inspired Genetic Algorithms and deep-learning regressors).
- Properly document the data science work around the problem, along with conclusions, recommendations and suggested future work if applicable.
- Knowledge of Machine Learning Models Life Cycle Management is a plus.
- Knowledge of AutoML tools like DataRobot, DataIku is a plus.
- Machine Learning with Python (i.e. libraries such as scikit-learn, scipy and NN frameworks such as PyTorch, TensorFlow, Keras).
- Machine Learning knowledge (i.e. algorithms such as Linear Regressions, probabilistic estimators like Naive Bayes, biologically inspired Genetic Algorithms and Deep-Learning regressors).
- General Python 3 programming skills.
- Front-End/UI design with Python tkinter is a plus.
Are you in?
Then send in your application (CV, current grades and cover letter written in English collated into one document) as soon as possible.
The process will be ongoing and we will let you know as soon as we can if you move forward. Any questions? Please email email@example.com
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: 304155