Project Proposals for William Flynn Scholarship: IIndex page

Project Number: 10
Project Title: Global Computing: co-operation of autonomous and mobile entities in dynamic environments
Project Supervisor: Dr. Girijesh Prasad, Professor Martin Mc Ginnity

Background
The key idea of global computing is to harvest the idle time of internet connected computers which may be widely distributed across the world, to run a very large and distributed application. All the computer power is provided by volunteer computers, which offer some of their idle time to execute a piece of the application. The number of devices connected to internet is constantly growing. Today there are over 93 million connected hosts. The computing power of hand held devices such as PDA is constantly growing. Considering also the revolutionary expansion of mobile devices market such as cellular phones, the number of exploitable computing resources might be in the billion order in the near future. The challenge is to harness so many unused computing resources to build a very large parallel computer.

The Proposed Project
This project aims to harness the power of rapidly growing and changing computational environments composed of highly diverge interconnected devices over wide-area network (i.e. internet). In these environments, everything is dynamic: physical devices are mobile, connectivity and bandwidth are changing and computational processes and data migrate. The main objective is to develop techniques for engineering systems that are dependable, flexible, secure, robust and efficient. The project will focus on the following three key aspects:

¨ Design of systems composed of autonomous entities whose participation in the computation is dynamic and where activity is not centrally co-ordinated.
¨ Analysing and reasoning about the behaviour of such systems, both qualitative and quantitative, even when very large numbers of entities or interactions are involved.
¨ Avoiding and/or detecting undesirable behaviour through control of the system and/or its environment.

One of the most important issues in the above three aspects is methods for controlling the use of resources which facilitate stability and evolution of such systems, e.g. the utilisation of idle resources in a transparent way but not against their owners' wishes and interests.

The project aims at designing and building a platform for experimenting with global computing capabilities. It is proposed to make use of intelligent approaches based on dynamic fuzzy neural hybrid architecture with self-organising capabilities to accomplish the three key aspects set out above.

If you are interested in being considered for a studentship please contact
the Group Director, Professor T.M. McGinnity by email:
tm.mcginnity@ulst.ac.uk

or telephone: +44-(0)28-71375417.

See the current research section of this website for details on research projects pursued by existing PhD students