Project Loon, currently under Google parent Alphabet's experimental division X, has made a major breakthrough that might allow it to launch sooner than planned.
Project Loon looks to launch balloons into the stratosphere that will be able to provide internet connectivity to users on Earth. With the major breakthrough, it is said that the technology is much closer to becoming reality.
Project Loon Breakthrough Fueled By AI
In September 2016, it was reported that artificial intelligence technology allowed Project Loon to keep one of its balloons up in Peruvian airspace for 98 days. This was considered an impressive feat because of the difficulty of keeping the balloons at a certain spot for long periods of time, and it was made possible through machine learning. The balloon, through the technology, was able to adapt to wind conditions that would have previously blew it away into other locations.
According to a blog post by the X division, further advancements in this machine learning technology incorporated into Project Loon, however, has now allowed the deployment of fewer balloons and have them form a cluster to provide internet connectivity to a specific region. Previously, the plan was to create rings of balloons that sail across the globe, with the balloons to take turns in moving through regions to provide internet access.
Instead of having to find a way to keep the balloons at a certain distance from each other as they drift across the planet's airspace, the improved altitude control and navigation system of the balloons will now allow them to focus on a certain location, with the balloons for that area to only make small loops within the location instead of having to travel throughout the Earth.
"The reason this is so exciting is we can now run an experiment and try to give services in particular places of the world with 10 or 20 or 30 balloons, not with 200 or 300 or 400 balloons," said Astro Teller, the head of the X division.
The Future Of Project Loon
While X admits that the navigation algorithms utilized for Project Loon could still be improved and that testing, which has so far been mostly carried out in South America, will need to expand to other parts of the Earth, the breakthrough represents a good sign for the viability of Project Loon, both in terms of operations and economics.
With less balloons needed, the team would be able to complete a Project Loon network for a particular area in weeks and not months, with the balloons easier to launch and manage. In addition, with the fewer number of balloons needed, the costs of a Project Loon network will be driven down, which will make it more feasible for telecommunications partners.
Project Loon is now years closer to rolling out the final form of Project Loon, which aims to provide internet connections to remote and rural areas. Project Loon engineer Sal Candido said that the rollout for a fully-working Project Loon network will happen "much, much sooner," and for the people who will benefit from it, that is certainly good news.