MSc thesis project proposal

[2023] DL4RF: Deep Learning for Wireless Transmitter Efficiency Enhancement

The rapid growth of wireless communication and the increasing demand for high-speed data transfer have driven the development of 5G networks. A key challenge in 5G systems is improving the energy efficiency of wireless transmitters, especially in the context of mobile devices and base stations. High Peak-to-Average Power Ratio (PAPR) in Orthogonal Frequency Division Multiplexing (OFDM) signals can lead to decreased efficiency in power amplifiers, causing increased power consumption and reduced battery life in mobile devices.

This master's project aims to apply deep learning techniques, specifically autoencoder networks, to reduce the PAPR in 5G OFDM signals. By doing so, the project seeks to enhance the energy efficiency of wireless transmitters in mobile phones and base stations, thus improving overall system performance and user experience.


  1. Conduct a literature review on PAPR reduction techniques in OFDM systems, focusing on deep learning approaches and their potential benefits.
  2. Investigate the properties and requirements of 5G OFDM signals to identify potential improvements through deep learning-based PAPR reduction techniques.
  3. Design and implement a deep learning-based autoencoder network for PAPR reduction in 5G OFDM signals.
  4. Develop a simulation environment to generate and process OFDM signals, incorporating the proposed autoencoder network.
  5. Evaluate the performance of the proposed deep learning-based PAPR reduction technique in terms of PAPR reduction, energy efficiency, and impact on signal quality, comparing it to traditional PAPR reduction methods.
  6. Optimize the autoencoder network for efficient implementation on mobile devices and base stations, considering computational complexity and memory requirements.
  7. Document the project's findings and contribute to the development of a final report or publication.


  1. Background in wireless communications and signal processing.
  2. Familiarity with 5G networks and OFDM systems.
  3. Knowledge of deep learning techniques.
  4. Proficiency in programming languages (e.g., Python) and deep learning frameworks (e.g., TensorFlow, PyTorch).


dr. Chang Gao

Electronic Circuits and Architectures Group

Department of Microelectronics

Last modified: 2023-03-22