Mobile Phone Processing As A Service?

Image by ronin691 via Flickr

Technology Review has an interesting article
about a research project, from Intel Research, where researchers have
built a technology that taps into the Cloud for the processing power
needed to do complex tasks on a mobile phone. The project, titled CloneCloud, integrates Cloud Computing to Smart Phones seamlessly. CloneCloud uses
the nearby computers or Datacenters to offer powerful processing power
to the Smart Phones.

It is my strong opinion that we are slowly moving
away from an era where we needed powerful computing devices to manage
various tasks in our daily lives. With the advent of Cloud based
technologies, the need for powerful devices are slowly becoming redundant. We should be able
to use barebones devices to do complex tasks by tapping into the Cloud
for the processing power. The lack of availability of nearly ubiquitous
internet connection and latency in the current day network is keeping us away from
going lean on local devices. But I am very confident that we will soon
be living in such a world. I visualize a world where the devices we use
will just serve as a entry point and the real processing will happen in
the Clouds.

CloneCloud is one such attempt where a Smart Phone
is cloned and kept in the Cloud. The mobile phone can, then, tap into
the Clouds for virtually unlimited processing power and storage. When
an user uses the Smart Phone for a particular task, the processing is
done on the Clouds without the user even realizing it. It is not like
the SaaS applications where the processing is done on the Cloud and the
user interacts only through a browser. In this case, the user will be using the various apps and other functionality on the phone. It is just that the
clone on the Cloud is much more powerful than the actual Smart Phone and when the
user executes a particular task, it is done either on the phone or on the
Cloud depending on the resources needed for the task. According to the
TR article, CloneCloud makes the Smart Phones not just more efficient but also more capable.

A
test application developed by Chun performs face recognition on photos.
It required 100 seconds of processor time on a standard Android phone,
but it finished in only one second when run by a clone of the phone
running on a desktop computer. Because the software runs on a
cloud-computing platform, it can be scaled in terms of the amount of
both memory allocated and processing power, both of which increase
performance on computationally intensive tasks.

It is still
in early stages of conceptualization. There is a long way to go before
it enters the mainstream market. There are security issues to be taken
care of. The carriers must drastically improve their network performance before
the users can have a seamless experience. However, I like this idea
because it is a very good use case for Cloud Computing. It shows how we
can use the Cloud to make lean devices be more efficient and capable. It
also goes to confirm my belief that the days of powerful devices in our
hand are coming to an end and the era of tapping into the Clouds for all
our needs is just around the corner. This technology may or may not see
the day light but it is of great academic interest and has a
potential to be really disruptive.

Related Posts:

• The Cell-Phone Aware PC May Be a PC-less PC