NORMA eResearch @NCI Library

Optimisation of Internet Bandwidth and Application Latency using the Edge Cloud and Machine Learning of IOT data

Doherty, James (2015) Optimisation of Internet Bandwidth and Application Latency using the Edge Cloud and Machine Learning of IOT data. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (9MB) | Preview


After Cloud computing the Internet of Things (IOT) has been heralded as the next step in the evolution of the Internet. A central concern is the integration of the IOT and the Cloud, which faces significant challenges. Gartner, the worlds leading information technology research and advisory company, predicts that by 2020 there will be over 26 billion connected devices exchanging data and information over the Internet. With this significant growth in data will come challenges such as increased network load and application latency.

Nielsen's Law of Internet Bandwidth indicates that connection speeds grow by only 50% per year. Therefore it becomes apparent that an approach is required to address future limitations. To overcome some of these issues recent developments in this field have seen applications moving to the data, to create the Edge Cloud. In effect it switches the current method around, which, in the centralised data centre model of Cloud Computing, brings the data to the application.

This paper proposes the use of an Intelligent Agent on the Edge Cloud to deliver workload optimisation between the Cloud and the Edge Cloud through Machine Learning. These Agents utilise Artificial Intelligence to map future events based on past analysis of IOT data. While recent research has illustrated the need for Smart Gateways to pre-process and trim data, this paper proposes to implement a means of learning from past actions taken which will be hosted on the Edge Cloud. It is proposed that, over time, improvements will be seen in the usage patterns of scalable Cloud resources, as well as a reduction in the network load and improvements in application latency.

Item Type: Thesis (Masters)
Subjects: T Technology > T Technology (General) > Information Technology > Cloud computing
Divisions: School of Computing > Master of Science in Cloud Computing
Depositing User: Caoimhe Ni Mhaicin
Date Deposited: 12 Oct 2015 09:27
Last Modified: 05 Feb 2016 10:12

Actions (login required)

View Item View Item