Edinburgh Data-Intensive Research

C2MS: Dynamic Monitoring and Management of Cloud Infrastructures

Gary.McGilvary — Tue, 07 Jul 2015 13:03:10 +0000

Ad hoc Cloud Computing

Gary.McGilvary — Tue, 07 Jul 2015 12:12:20 +0000

Speaker(s):

Presentation Type:

talk

This presentation presents the first complete, integrated and end-to-end solution for ad hoc cloud computing environments. Ad hoc clouds harvest resources from existing sporadically available, non-exclusive (i.e. primarily used for some other purpose) and unreliable infrastructures. In this presentation we discuss the problems ad hoc cloud computing solves and outline our architecture which is based on BOINC.

Thank you to the EPSRC UK-USA HPC Collaboration Grant (http://ukusahpc.blogspot.co.uk) for funding this trip.

Attachment	Size
Adhoc_Cloud_Computing_2015.pdf	1.41 MB

Date and time:

Saturday, 27 June, 2015 - 15:00

Location:

IEEE Cloud, New York, USA

Evolutionary Computation and Constraint Satisfaction

Jano.van.Hemert — Wed, 27 May 2015 07:21:35 +0000

Ad hoc Cloud Computing

Gary.McGilvary — Fri, 24 Apr 2015 13:57:21 +0000

Congratulations to Gary McGilvary on his PhD

Malcolm.Atkinson — Wed, 10 Sep 2014 07:56:08 +0000

We should all congratulate Gary on completing his corrections and on managing remote production of his thesis, "Ad hoc Cloud Computing", while in California, interning at Apple. It demonstrates the remarkable power of the Internet to arrange action at a distance! His thesis is now available here and should be read.

Gary's research, "Ad hoc Cloud Computing" is a much more remarkable and sustained demonstration showing how the unused power of an organisation's computers or altruistically offered computers can be harnessed effectively and made much more usable. He explored every step needed to make it easy to set up Volunteer Clouds, i.e., how to provide and manage a consistent and reliable Cloud running over unreliable, heterogeneous volunteer computers. He devised a technically elegant and practical approach to every stage, building on BOINC. He measured these carefully to demonstrate their power and efficiency.

But you don't want to hear about it from me, you should read his thesis, which I am glad to report is on this site, http://research.nesc.ac.uk/node/994. Please download it and have a good read; I enjoyed it every time I read it! His examiners primary concern was that more people should read and understand it, as they thought it was excellent research that should be widely applied.

Topic of this submission:

Success story

Research topics:

New conceptual models for systems