NORMA eResearch @NCI Library

A Comparative Study on Cloud Gaming performance using Traditional, Containers in Fog Nodes, and Edge-enabled Shared GPU architectures

Muralikrishnan, Sabesan (2021) A Comparative Study on Cloud Gaming performance using Traditional, Containers in Fog Nodes, and Edge-enabled Shared GPU architectures. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (3MB) | Preview
[thumbnail of Configuration manual]
Preview
PDF (Configuration manual)
Download (1MB) | Preview

Abstract

The demand for cloud gaming and the user base for the same has increased drastically following various advancements in the field. After the introduction of cloud computing and its continuous evolution, various new technologies like Fog Computing, Edge computing were developed. These advancements are leveraged to overcome all fallacies and pitfalls in the traditional cloud gaming solution. Since the introduction of Edge Computing, major changes happened in the mobile network region. The new 5G technology allows users to experience a high-speed internet connection in their mobile devices. While the Edge Nodes are primarily used to collect raw data and share them with the cloud server for processing, in this research project, one more implementation for Edge Computing is inspired and proposed as a cloud gaming model. We have leveraged Edge Computing nodes, powered by virtual GPU, coupled with WebRTC streaming, in an attempt to improve the Quality of Experience and Quality of Service. The game commands will be sent to the cloud server through Edge Node. Once the game video is rendered at the cloud server, it will be encoded on an Edge Node closer to the user. This encoded video will be then streamed as real-time video onto the player’s browser. The communication will pass only through the Edge Node without any additional hops. The evaluation result proves that the proposed solution maintains a constant frame rate, frame delay time below 10 ms, jitter rate below 10, and 30% reduced bandwidth consumption, thus improving the overall QoE and QoS.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Cloud computing
G Geography. Anthropology. Recreation > GV Recreation Leisure > Games and Amusements > Online Games
Divisions: School of Computing > Master of Science in Cloud Computing
Depositing User: Tamara Malone
Date Deposited: 29 Nov 2022 16:37
Last Modified: 08 Mar 2023 15:22
URI: https://norma.ncirl.ie/id/eprint/5941

Actions (login required)

View Item View Item