Master thesis – Neuromorphic computing in Wireless

Location: Kista, Stockholm

Preferred starting date: Jan. 2025

Extent: 1-2 student, 30hp.

About the company

Founded in 1988, Huawei Technologies is one of the fastest growing telecommunications and network solutions providers in the world. At Huawei Technologies, we look for people who share our vision: to enrich life with communication. We are a leading supplier of next generation telecom networks and currently serve 37 of the world’s top 50 operators. Our people are committed to providing innovative products, services and solutions and understand it as their mission to create long-term value and growth potential for our clients.

The Huawei office in Sweden is the leading overseas R&D office in Huawei, and the Wireless Algorithm group at Huawei Sweden drives innovation for the Huawei Wireless RAN product. We work on both advanced receivers and on Radio Resource Management algorithms, for both LTE and 5G.

Thesis description

5G is posing high requirements on data rate and one alternative to achieve this is to increase the number of antennas on both transmitter and receiver, which is known as MIMO system. While this technology offers significant advantages, it also presents substantial computational and energy-efficiency challenges. Traditional signal processing techniques for MIMO detection and beamforming often involve complex matrix operations, such as matrix inversions and large-scale optimizations, which require significant computational resources. As wireless networks scale to serve more users with higher data rates, these computational demands become increasingly difficult to meet, especially when real-time processing is required.

In recent years, deep learning (DL) techniques have been explored to reduce the computational burden of MIMO detection and beamforming. However, the use of artificial neural networks (ANNs) comes with high energy consumption due to the need for intensive multiply-accumulate operations. In contrast, Spiking Neural Networks (SNNs), which are inspired by the event-driven communication model of the brain, have shown great promise in reducing energy consumption while maintaining competitive performance. Unlike ANNs, SNNs rely on discrete spikes to communication and process information, leading to energy-efficient computation.

In this thesis, you will explore and demonstrate the potential of SNNs as an energy-efficient alternative to conventional neural networks and traditional methods for solving key challenges in MIMO detection and beamforming. By leveraging the unique characteristics of SNNs, such as event-driven processing and low-computational overhead, this research seeks to reduce power consumption while maintaining or improving performance in terms of detection accuracy and beamforming efficiency.

Qualifications

• Master student in Electrical Engineering or equivalent.
• A solid theoretical background in areas such as information theory and signal processing.
• Experience in modeling and link level simulation.

• Good knowledge in simulators.

Contact person

Jinliang Huang

jinliang.huang@huawei.com