Consultez nos dernières offres similaires
Contenu de l'offre Data Scientist Internship – Optimization of RRM procedures in 5G Networks: Machine learning based approaches chez NOKIA
Nozay (91)
Stage
Nokia is a global leader in the technologies that connect people and things. With state-of-the-art software, hardware and services for any type of network, Nokia is uniquely positioned to help communication service providers, governments, and large enterprises deliver on the promise of 5G, the Cloud and the Internet of Things.
Serving customers in over 100 countries, our research scientists and engineers continue to invent and accelerate new technologies that will increasingly transform the way people and things communicate and connect.
Nokia is an equal opportunity employer that is commited to diversity and inclusion.
At Nokia, employment decisions are made regardless of race, color, national or ethnic origin, religion, gender, sexual orientation, gender identity or expression, age, marital status, disability, protected veteran status or other characteristics protected by law.
Context
Within the Mobile Networks Business Group, in the 5G product architecture department, we are implementing solutions based on Artificial Intelligence approaches, in order to optimize the performance of mobile access networks.
This internship fits into exploratory projects conducted in our department, and aiming at the introduction and the implementation of machine learning techniques in 5G networks.
The considered applications domain is the allocation and the optimization of radio resources for Multi Users massive MIMO systems in 5G. Beamforming, scheduling, traffic load balancing, QoS / QoE management and contextualized data mining are some practical examples of optimization.
Role
In this context, the main objective of the internship is to contribute in the introduction of machine learning algorithms in radio resource management procedures for 5G networks.
This requires fundamental skills in machine learning from model design to implementation and a good know-how of alternative ML approaches (such as reinforcement, supervised, unsupervised or hybrid). Knowledge, of optimization techniques such as Transfer Learning / Federated Learning and of ways to implement them considering the level of complexity they introduce, is required as well.
It is also necessary to have a good understanding of the implementation constraints in the products, such as inference latency, availability of data, in order to select the learning method tailored to the problem.
The validation of the proposed solutions would consist in assessing the benefit of the machine learning based approaches compared to the conventional methods. This validation will be performed on a software platform embedding the usual libraries in machine learning (e.g. Keras, PyTorch) and / or Nokia platform.
Your mission will consist in:
1.Getting familiar with the procedures for radio resources allocation in 5G networks
2.Selecting one (or more) specific use cases and identifying the necessary optimizations taking into account the RAN constraints
3.Identifying from the state-of-the-art methods, the most suitable candidate machine learning methods, to solve the problem.
4.Validating the proposed solution on Machine Learning software platform or on Nokia HW platform.
At the end of this internship, this experience will allow you to reinforce and put into practice:
Your theoretical expertise in Machine learning Algorithms,
Your knowledge in mobile radio communications, especially 5G networks,
A methodology for analysis / exploitation of large volumes of data as well as for validation of machine learning algorithms.
Qualification:
Study: Master, Engineer or PhD with specialization in Machine Learning and/or telecommunications, wireless networks or information theory.
Expertise in Machine Learning is required.
Knowledge in wireless radio communications, telecommunication is highly recommended.
It is mandatory to have good level in programming: Python (Keras, PyTorch), Matlab, C++.
Good level in English is mandatory (Oral and written).