Deep learning based channel state information compression for 5G system

• Main Author: Tan, Norman Rui Qiang
• Other Authors: Teh Kah Chan
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2023
• Subjects: Engineering::Electrical and electronic engineering::Wireless communication systems
• Online Access: https://hdl.handle.net/10356/167114
• Institution: Nanyang Technological University

With the increasing demand for high-speed wireless communication and the emergence of new technologies such as the Internet of Things (IoT), the 5G wireless communication system has gained significant attention in recent years [1]. Channel state information (CSI) is a critical aspect of wireless communication that describes the current state of the channel between the transmitter and receiver. However, CSI is typically high-dimensional and requires significant overhead to transmit, which can lead to increased power consumption and reduced network efficiency [2]. To address this issue, this report proposes a deep learning-based approach for compressing CSI in 5G systems. A dataset of CSI measurements is collected from a real-world 5G system, DeepMIMO, to generate results. Overall, the proposed deep learning-based approach provides an efficient solution for compressing CSI in 5G systems. By using a compressed representation of the CSI data, we can reduce the overhead of transmitting CSI information, leading to improved network efficiency and reduced power consumption. This approach has the potential to be applied in a wide range of wireless communication systems and can pave the way for the development of more efficient and reliable communication technologies [3].