Sensor data processing at the 5G edge
Loading...
URL
Journal Title
Journal ISSN
Volume Title
Sähkötekniikan korkeakoulu |
Master's thesis
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Authors
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, StephanThesis advisor
Rouvala, MarkkuKeywords
fifth generation wireless (5G), artificial intelligence, Light Detection and Ranging (LiDAR), machine learning, edge processing