Cloud Computing Distributed Infra-Structure

Back when I was working on my graduation project in 2006, Normal cellphones were quickly being replaced with smartphones. Distributed computing projects such as the Great Internet Mersenne Prime Search (which was doing a cool 30 teraflop by 2006) were getting a lot of media exposure at the time, users donating their computers idle time for causes they believed in, thus becoming nodes in a distributed computer that spanned the globe. I had this epiphany, using smart phones within the context of such a project; Using the other wise wasted idle processing powers sitting in people’s pockets for greater good, maybe even rent it from them. I went as far as writing a paper about that. then forgot all about it.

Smart phones weren’t even half as powerful as they are now, Communication infra-structure was several times slower. The concept of pockets full of distributed computing sounds perfect for the day and age. The concept is quite logical, you rent your phone’s idle time, so whenever your phone is in your pocket it generates money for you, selling your phone’s idle time to the highest bidder. A whole new market would be created over night for idle processing power, with portals the smartphone owners can register in, download an application that allows their phones to receive these distributed tasks, on the other hand people with jobs that would require a massive processing power (such as graphics rendering) can submit their tasks to that portal and have it distribute it for them. With a clever billing system in the background matching bids to offers making sure both parties make the most of that system.

The implementation of such a simple is quite simple really, actually similar systems that rely on computers rather than cellphones have already reached a working formula that’s proved its stability over the years. A central system breaks down the larger process into a set of manageable tasks, these tasks are then sent out for processing, the system has built in precautions against someone injecting wrong data into it, this is done through sending the same task to several users hence ruling out any inconsistent results. It’s surprisingly reliable and robust, much more than any other currently available similar infrastructure anyway. In a way its true cloud computing in the sense that even the hardware is cloud like.

I believe its only a matter of time before this becomes mainstream, its only a matter of time before you get to buy tablets/phones/laptops with subsidized prices that are constantly selling its excess processing power to cloud based datacenters.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s