Sensor data processing at the 5G edge

Loading...
Thumbnail Image

URL

Journal Title

Journal ISSN

Volume Title

Sähkötekniikan korkeakoulu | Master's thesis

Date

2024-08-19

Department

Major/Subject

Communications Engineering

Mcode

ELEC3029

Degree programme

CCIS - Master’s Programme in Computer, Communication and Information Sciences (TS2013)

Language

en

Pages

59+12

Series

Abstract

With the development of cellular networks in the form of 5G, many new use cases have deemed to be possible and practical to implement. This has been supplement-ed by the developments of other technologies and disciplines such as artificial intel-ligence (AI) and chip design. These use cases vary from autonomous driving to re-mote surgery, but they all have one thing in common- enormous generation of data. Depending on the use case, there are varying requirements of time taken to acquire data, process it, come to an inference and act upon it. This requires large computa-tional capabilities while minimizing latency, which is solved through the concept of edge computing. For an application of lidar sensing implemented as a 5G use case scenario, there is lack of a definitive qualitative and quantitative study of realizing it on an edge platform. The work presented in this thesis deals with processing of 3D point cloud data obtained from a LiDAR sensor in a smart city environment on a state-of-the-art edge platform and assesses the memory and power consumption to determine its feasibility and optimization. This is compared with processing on a research workstation.

Description

Supervisor

Sigg, Stephan

Thesis advisor

Rouvala, Markku

Keywords

fifth generation wireless (5G), artificial intelligence, Light Detection and Ranging (LiDAR), machine learning, edge processing

Other note

Citation