Find solution
What is cloud computing?

How can academics do the right things on cloud computing research, and what are the hardest challenges?

  • Cloud computing leaders from industry seems always keep their lips sealed when talking about what they are doing. Moreover, in a university setting, there is no way to build real world cloud infrastructure. This makes it hard for academics to know what the real challenges cloud computing is facing. Sometimes incorrect assumptions about the real-world cloud lead to irrelevant works. So here comes my question: How can academics do right thing on cloud computing research, and what are the hardest challenges? Voices from industry and academics are both welcomed.

  • Answer:

    I think you're looking at the issue too broadly. 'Cloud Computing' is really an industry term; from a technical and academic point of view there really is no such thing. However there are numerous sub-fields which compose the field as a whole, so in order to conduct research in the area you'll need to work out precisely the problem you're trying to solve and use that as your starting point. The majority of the open research issues faced by cloud computing aren't that much different than what's been the focus of distributed computing research for the last decade. The popularity of cloud technologies are due to them becoming viable thanks to the decreased cost of processing capacity and bandwidth. So off the top of my head, some of the sub-fields you can break cloud computing down into would be Software as a Service, Storage as a Service, Platform as a Service, and information security (some of the work being done in homomorphic encryption is amazing: http://www.i-programmer.info/news/112-theory/2330-darpa-spends-20-million-on-homomorphic-encryption.html). The idea of using the could of large-scale distributed processing is also being bandied around, however I believe that's inevitably going to run into the same latency limitations faced by all similar projects (ie. it'll only be useful for embarrassingly parallel problems that we already know how to solve). To summarise: cloud computing is broad a starting point for research. You'll need to focus much more in a very specific area of distributed computing and work from there. For some ideas to get started, check out the proceedings of some recent conferences in the field,

Alistair Atkinson at Quora Visit the source

Was this solution helpful to you?

Other answers

They don't.  As other answers have said, cloud computing is an industry buzzword, covering many, many different things, most of which are at best an evolution of existing practices.  If you want to do good science and good research, start by focusing on a problem, not on a technology or industry terminology.  Note that this doesn't mean you don't work with industry; I do all the time, and use the right terminology as needed.  But from a research perspective, start with the problem.

Paul A.S. Ward

I sort of agree with Alastair's answer - it's true if you see the question as being about 'what are the research challenges in implementing clouds'. On the other hand, if you think rather more broadly, then some key long-term academic research challenges are: What computational models should we be using for cloud computing? Map-reduce is the one that everyone uses but what are the alternatives? How do we understand the storage/computation trade-offs in a world where we are managing petabytes of data? How do we use the cloud to manage this data? How do we substitute storage for computation and vice-versa? How do we design elastic algorithms that can adapt to 'infinite' computing resources? When should we stop scaling out? How do we model and reason about the performance and dependability of cloud-based systems? From an enterprise perspective, how can legacy systems be migrated to the cloud to take advantage of the elastic capabilities?

Ian Sommerville

Here is a great blog post of Matt Welsh about your question: http://matt-welsh.blogspot.com/2011/05/how-can-academics-do-research-on-cloud.html

Dave Burke

Related Q & A:

Just Added Q & A:

Find solution

For every problem there is a solution! Proved by Solucija.

  • Got an issue and looking for advice?

  • Ask Solucija to search every corner of the Web for help.

  • Get workable solutions and helpful tips in a moment.

Just ask Solucija about an issue you face and immediately get a list of ready solutions, answers and tips from other Internet users. We always provide the most suitable and complete answer to your question at the top, along with a few good alternatives below.