Master Thesis: Latency-Aware AI-Assisted Codebook MU-MIMO Pairing
Ericsson ABNy
Beskrivning
Join our Team
About this opportunity
We are looking for master thesis students who want to explore how AI methods can improve real-time scheduling decisions in Codebook MU-MIMO. In MU-MIMO, the base station schedules multiple user equipments simultaneously to improve spectral efficiency and cell throughput. Therefore, selecting suitable UE pairs or groups is an important part of the scheduling process.
This thesis focuses on exploring how AI methods can reduce the computational complexity and scheduler latency of the existing deterministic MU-MIMO pairing algorithm, while maintaining high pairing quality, throughput, and spectral efficiency. For example, AI can be used to rank or prune candidate UE pairings and identify the most promising candidates before the existing pairing algorithm is applied
What you will do
• Explore how AI can be integrated into the existing MU-MIMO pairing process, with the goal of reducing computational complexity and scheduler latency while maintaining high pairing quality and system performance.
• Investigate and evaluate different ways of applying AI to the pairing process, for example, by using AI to rank or prune candidate UE pairings before the existing pairing algorithm is applied.
• Compare the AI models and approaches explored in terms of pairing performance, model complexity, computational cost, and latency.
The skills you bring
• Background in machine learning and AI, preferably with hands-on experience using models such as LSTMs, CNNs, or other ML models.
• A good foundation in communication systems; a background in wireless communication or other communication-related fields is a plus.
• Experience with model experimentation, debugging, evaluation, and performance analysis.
• Interest in AI/ML, AI in RAN, intelligent networks, or next-generation wireless communication.
• Good programming and data analysis skills.
• Good communication and collaboration skills.
Why join Ericsson?At Ericsson, you'll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what's possible. To build solutions never seen before to some of the world's toughest problems. You'll be challenged, but you won't be alone. You'll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.
What happens once you apply? Click Here to find all you need to know about what our typical hiring process looks like.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) || Lund
Req ID: 792420
About this opportunity
We are looking for master thesis students who want to explore how AI methods can improve real-time scheduling decisions in Codebook MU-MIMO. In MU-MIMO, the base station schedules multiple user equipments simultaneously to improve spectral efficiency and cell throughput. Therefore, selecting suitable UE pairs or groups is an important part of the scheduling process.
This thesis focuses on exploring how AI methods can reduce the computational complexity and scheduler latency of the existing deterministic MU-MIMO pairing algorithm, while maintaining high pairing quality, throughput, and spectral efficiency. For example, AI can be used to rank or prune candidate UE pairings and identify the most promising candidates before the existing pairing algorithm is applied
What you will do
• Explore how AI can be integrated into the existing MU-MIMO pairing process, with the goal of reducing computational complexity and scheduler latency while maintaining high pairing quality and system performance.
• Investigate and evaluate different ways of applying AI to the pairing process, for example, by using AI to rank or prune candidate UE pairings before the existing pairing algorithm is applied.
• Compare the AI models and approaches explored in terms of pairing performance, model complexity, computational cost, and latency.
The skills you bring
• Background in machine learning and AI, preferably with hands-on experience using models such as LSTMs, CNNs, or other ML models.
• A good foundation in communication systems; a background in wireless communication or other communication-related fields is a plus.
• Experience with model experimentation, debugging, evaluation, and performance analysis.
• Interest in AI/ML, AI in RAN, intelligent networks, or next-generation wireless communication.
• Good programming and data analysis skills.
• Good communication and collaboration skills.
Why join Ericsson?At Ericsson, you'll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what's possible. To build solutions never seen before to some of the world's toughest problems. You'll be challenged, but you won't be alone. You'll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.
What happens once you apply? Click Here to find all you need to know about what our typical hiring process looks like.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) || Lund
Req ID: 792420
Ansök till tjänsten
Master Thesis: Latency-Aware AI-Assisted Codebook MU-MIMO Pairing
Ny
OM FÖRETAGET
Ericsson AB
