Software defined networking controlled energy optimization through traffic prediction on microwave access network

Thumbnail Image

Files

master_Rivi_Gabriele_2023.pdf (1.48 MB)

URL

Journal Title

Journal ISSN

Volume Title

Perustieteiden 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

2023-10-09

Department

Major/Subject

Data Science

Mcode

SCI3115

Degree programme

Master's Programme in ICT Innovation

Language

en

Pages

78

Series

Abstract

The work proposed in this Master’s Thesis presents a new approach at achieving energy optimization on components deployed across a Mobile Access Network using Traffic Prediction. Specifically, the study proposes a solution employing a probabilistic Deep Learning forecasting model that uses nodes’ historical data to provide expected future traffic patterns. The expected traffic is then used to propose a shutdown schedule for network components, ultimately reducing energy consumption. This work also produces a working and customizable architecture, prototyping a pipeline to develop customer-centric solutions, identifying the building principles and aspects to consider to include AI-services successfully in a Software Defined Architecture.

Description

Supervisor

Jung, Alexander

Thesis advisor

Rodriguez, Raquel

Keywords

traffic prediction, deep learning, probabilistic forecasting, mobile access networks, energy efficiency, resource scheduling

Other note

Citation

Permanent link to this item

https://urn.fi/URN:NBN:fi:aalto-202310156410

Collections

[dipl] Perustieteiden korkeakoulu / SCI