Internship | AI/ML-based Radio Network Management for Energy Savings in 6G Networks

A number of enablers are researched for adoption in the targeted 6G mobile network technology, incl. ultra-massive MIMO beamforming, network ultra-densification and cell-free networking, largely aiming to fulfil the needs of ever-growing mobile traffic. Although network equipment and devices have been and still will be made more energy-efficient, it is expected that this cannot fully compensate the increasing rate of mobile traffic volumes. This may very likely lead to higher energy consumption in 6G networks in comparison with current mobile networks. Energy-aware radio network management has the potential to minimise energy consumption in a 6G network. Two general principles are: (1) at the network level, 6G networking resources (base stations, antennas) can be dynamically switched on/off in response to spatio-temporal traffic fluctuations, while maintaining coverage and ensuring sufficient capacity; (2) at the link level, each individual device is generally served by the nearest base station and with a highly directional transmission beam in order to optimise transmission efficiency. Heuristic network management solutions have been used for energy saving in legacy mobile networks (4G/5G), where a portion of network capacity (base stations, carriers) may be dynamically turned off at low (predicted) traffic demand while the network coverage is guaranteed. Model-based approaches are among others limited by the inaccuracy of the energy consumption model of a base station; and of the predicted traffic demand fluctuations. 6G networks are envisioned to be characterised by a very high base station deployment density (remote radio units), high degrees of MIMO beamforming, incl. the use of distributed MIMO (D-MIMO; where multiple base stations jointly serve a given UE), and the use of powerful centralised RAN solutions allowing the application of AI/ML methodologies in radio network management for the purpose of a.o. energy savings. These 6G advancements are anticipated to provide a high potential for dynamic energy saving solutions, where both radio units and associated (typically more centralised) processing resources can be highly dynamically switched on/off upon need and active radio units can be controlled to intelligently utilise (D-)MIMO beamforming to ensure a high degree of service coverage and quality, and provide sufficient capacity to match the current traffic load.

Key activities of the proposed graduation project are:

• To conduct a thorough literature review concerning both model-based and AI/ML-based energy savings for 6G radio networks, considering (de)activation of both radio units and corresponding processing resources, as well as concerning cell-free networking/D-MIMO solutions, in order to provide a solid research basis, aid in modelling and potentially further sharpen the problem formulation to ensure novelty.
• To define a limited set of challenging scenarios with gradually increasing complexity, which will form the basis for the solution development and assessment. We aim to consider ultra-massive MIMO beamforming, the use of sub-THz spectrum, network ultra-densification and cell-free networking/D-MIMO in one or more of these scenarios.
• To model all relevant scenario aspects related to e.g. network layout, key BS/UE/traffic characteristics and the propagation environment.
• To develop one or more AI/ML-based energy saving solutions (including identified algorithms and in/outputs), operating in conjunction with adaptive beamforming algorithms. Formulate one or more heuristic solutions that can be used as a baseline.
• To develop a system-level simulator incorporating all model and solution aspects.
• To utilise aforementioned simulator to conduct an extensive quantitative assessment of the proposed AI/ML-based and heuristic solutions for a range of relevant scenarios and possibly distinct optimisation timescales.
• To derive key insights and conclusions w.r.t. the optimization solution, the attainable energy savings and coverage/performance effects, the sensitivity thereof to selected scenario aspects and complexity issues related to the algorithm execution itself, implementational feasibility and training aspects.

The MSc project will be conducted as part of the large nationally funded research programme ‘Future Network Services’, bringing together 50-60 partners for a targeted period of six years, incl. leading mobile network operators and equipment vendors. The proposed MSc project is envisioned to involve collaborations/regular interactions with FNS partners.

You are a graduate student pursuing a master’s degree, preferably in the direction of Electrical Engineering or Computer Science. You have affinity with / interest in mobile networks, computer simulations, machine learning and have programming experience. You have an enterprising, flexible and cooperative nature. You are also communicative, creative and innovative. Duration of the graduation project is about nine months.

You want to work on the precursor of your career; a work placement gives you an opportunity to take a good look at your prospective future employer. TNO goes a step further. It’s not just looking that interests us; you and your knowledge are essential to our innovation. That’s why we attach a great deal of value to your personal and professional development. You will, of course, be properly supervised during your work placement and be given the scope for you to get the best out of yourself. Naturally, we provide suitable work placement compensation.

At TNO, we innovate for a healthier, safer and more sustainable life. And for a strong economy. Since 1932, we have been making knowledge and technology available for the common good. We find each other in wonder and ingenuity. We are driven to push boundaries. There is all the space and support for your talent and ambition. You work with people who will challenge you: who inspire you and want to learn from you. Our state-of-the-art facilities are there to realize your vision. What you do at TNO matters: impact makes the difference. Because with every innovation you contribute to tomorrow’s world. Read more about TNO as an employer.

At TNO we encourage an inclusive work environment, where you can be yourself. Whatever your story and whatever unique qualities you bring to the table. It is by combining our unique strengths and perspectives that we are able to develop innovations that make a real difference in society. Want to know more? Read what steps we are taking in the area of diversity and inclusion.

After the first CV selection, the application process will be conducted by the concerning department. TNO will provide a suitable internship agreement. If you have any questions about this vacancy, you can contact the contact person mentioned below.