About this opportunity:

Mobility and handover have always been one of the most researched topics in 3GPP standardization body for different generations of telecommunication standard. The L3 handover process involves the UE sending measurement reports to the source cell, which decides on a handover based on signal strength and quality metrics. Despite its importance, L3 handover has shortcomings, such as longer handover interruption which can lead to late handovers and potential service interruptions in case of handover and radio link failures (RLF). L1/L2 Triggered Mobility (LTM) aims to reduce handover interruption time and mobility overhead in mobile networks by leveraging lower layer signalling. The LTM process involves preparing the UE with candidate cells RRC configuration in advance, UL and DL pre-synchronization with the target cell while maintaining the source cell connection and executing a cell switch with minimal interruption using Medium Access Control (MAC) layer signalling. This approach reduces handover interruption to 20-30ms in LTM from a handover interruption of 50-90ms in L3 handover, making LTM suitable for services requiring high bitrate and low latency.

3GPP Rel-19 explores the utilization of artificial intelligence and machine learning (AI/ML) to enhance mobility performance for L3 handovers. The related study covers the aspects of AI/ML based radio measurements predictions over the time-domain, spatial-domain, and frequency-domain, which facilitate in the prediction of L3 handover events, ping-pong handovers, and RLF. The application of AI/ML algorithms to L3 handover aims at enhancing handover performance KPIs, e.g., reducing the number of ping-pong handovers, RLFs and handover failures.

What you will do:

The thesis topic covers the application of AI/ML algorithms to enhance the performance of LTM handover. The thesis aims at studying the application of AI/ML algorithms in predicting the lower layer (L1/L2) radio measurements which in turn enable in the prediction of the fulfillment of LTM handover events. I.E, the prediction model assists the network in finding out whether the entering/leaving conditions associated to a certain LTM handover event shall be fulfilled to perform more informed handover decision. The tasks of the thesis include:

•   Understanding of the key concepts related to LTM handover 
•   Investigating the potential AI/ML prediction models which can be applied for predicting the LTM handover events
•   Running LTM handover simulations (using a Java-based simulator) without AI/ML predictions
•   Apply AI/ML for LTM HO event prediction
•   Training the AI/ML model with lower layer radio measurements for LTM handover event predictions
•   LTM performance evaluation with AI/ML prediction model (using Java-based and Python-based simulators)
•   Embed the predicted events (or radio measurements) in the mobility flow within the simulator
•   Investigating HO performance KPIs (e.g., ping-pong handover, handover failures, time of stay, timely UL/DL pre-synchronization with the target cell etc.) and AI/ML model KPIs (e.g., prediction accuracy, quantization error, measurement error, etc.) using MATLAB

The skills you bring:

•    MS. final year in Computer Science, Computer Engineering, Machine Learning, Electrical Engineering, or similar
•    Strong Programming skills (Java, Python, and MATLAB)
•    Knowledge of AI/ML algorithms
•    Fluent in English

Application:

Applications should include a transcript, a brief cover letter and CV, highlighting any previous activities or projects which are relevant to this position

​What happens once you apply?

Click Here to find all you need to know about what our typical hiring process looks like.

We encourage you to consider applying to jobs where you might not meet all the criteria. We recognize that we all have transferrable skills, and we can support you with the skills that you need to develop.

Encouraging a diverse and inclusive organization is core to our values at Ericsson, that's why we champion it in everything we do. We truly believe that by collaborating with people with different experiences we drive innovation, which is essential for our future growth. We encourage people from all backgrounds to apply and realize their full potential as part of our Ericsson team. Ericsson is proud to be an Equal Opportunity Employer. learn more.

Primary country and city: Sweden (SE) || Stockholm

Job details: Researcher

Primary Recruiter: Arvid Bergström