 Cloud Gaming Ecosystems THESIS TOPIC PROPOSAL Institute: Budapest University of Technology and Economics computer sciences Doctoral School of Informatics Thesis supervisor: Péter Babarczi Location of studies (in Hungarian): Department of Telecommunications and Media Informatics Abbreviation of location of studies: TMIT Description of the research topic: During the last years on-line multi-player video games became even more popular as they offered a space where people were able to hang out with their friends without leaving their home, thus, contributed to their mental health. This social trend and 2022 games industry acquisitions suggest that besides social media applications, video games will be a major part of people’s phone time on the road and also integrated in their home entertainment. As a first step, in the last few years all major gaming companies launched their own cloud gaming service, which can bring high-quality games to devices with low hardware requirements by moving the computationally intensive tasks from the phone/console to data centres and stream the game from there, thus, increasing accessibility to the benefits of video games to more players. However, this conceptual change raises several engineering challenges. The cloud gaming ecosystem consists of an ultra-reliable low-latency access (e.g., 5G mobile edge) network, the Internet backbone and an intra-data center network, as well as the servers running the video game in the edge or cloud equipped with appropriate GPUs. Although this ecosystem resembles several aspects of video streaming with already existing solutions, it requires further research to tailor these to a specific video game genre owing to the unique hardware requirements and highly interactive nature of the medium. The open research questions include but are not limited to: - Measure the end-to-end latency of different cloud gaming services, propose prediction models on technical parameters to provide minimum Quality-of-Experience. - Extend traditional skill-based matchmaking models with constraints based on technical parameters, propose novel matchmaking algorithms. - Allocate matches to edge servers or to the cloud considering hardware availability. Investigate possible function chain decompositions to meet latency requirements. - Design dynamic migration and topology adaptation algorithms which are well-prepared for failures and user mobility. - Investigate different hardware and software solutions to increase accessibility of video games for all gamers. Required language skills: English Number of students who can be accepted: 1 Deadline for application: 2024-06-19 |