Two years ago Microsoft placed a cylinder-shaped data container into the ocean. Interestingly enough, after being extracted from the sea only “eight out of the 855 servers on board had failed” (Cellan-Jones). Ben Cutler, who is leading the project compares the situation with the typical data center on land. Cutler states, “‘Our failure rate in the water is one-eighth of what we see on land.'” Analysts at Microsoft believe this “greater reliability” may be related to the lack of humans on board the data center and that nitrogen was being pumped into the capsule as opposed to oxygen. Likewise, the experiment is projected to make storing data more sustainable as “All of Orkney’s electricity comes from wind and solar power” (Cellan-Jones). Orkney, an archipelago off the coast of Scotland, was the location chosen for the experiment due to its energy practices.
Ultimately, I believe Microsoft is heading in the right direction with this project. With data optimization and data storage being increasingly important moving forward, Microsoft is getting ahead of the curve. I thought it was extremely interesting how the project, even though underwater, was actually more efficient and had fewer failures than a conventional data center. If these underwater centers turn out to have long term success, it could change the way data is stored forever. Likewise, with climate change becoming a larger problem, more sustainable centers will help with the increasing need for storage and cloud optimization. However, I do have one obvious concern for underwater data centers. If water manages to get into the base, that could ruin the storage servers inside. For this reason, I believe space could be a good place for data centers moving forward by utilizing satellites to serve as capsules for servers.
Overall, I am curious to see if Microsoft continues to create more underwater databases in the future. However, I could also see companies placing data centers into space for further optimization if problems arise.
Source: https://www.bbc.com/news/technology-54146718
I have never heard of an underwater data base until now and think it is a really interesting concept. I never thought about all the weather factors and human interaction that could have an impact on the success of the data. The article I read said that the failure rate was lower on the data base that was placed in the water. It will be interesting to see if Microsoft decides to switch to using more underwater data bases or stick with the ones they currently have on land. The accessibility of the ones on land is definitely a positive and there may be a cost different between the two. I am curious whether other companies will follow Microsoft’s lead and start to experiment with underwater data bases as well. This could be a start to a whole new level of data storage and ultimately change the way companies store their data forever. Two years is a long time, but also, a lot can happen in years after, so it is hard to tell the long term success of the underwater data base. It is good to see positive outcomes from the first two years though, and I think in the future more and more companies will start to implement underwater data storage as well.
Source: https://cacm.acm.org/news/247450-microsofts-underwater-datacenter-resurfaces-after-two-years/fulltext
When I first read the headline for this post, I had to read it again. I was so surprised to see that Microsoft had a data center underwater. At first, I thought this was a very random idea and was very confused on why Microsoft would want to try this. Then after doing some research and reading the main blog post, I realized how smart of an idea this was. As Paul Lilly wrote “Datacenters run hot—very hot—and it can be both challenging and expensive to keep them cool. The ocean is like the ultimate liquid cooling setup” (Lilly, 2020). This is one of the main benefits from storing a datacenter which is so smart since it is normally very hard to keep devices like these cool. I cannot believe that they got this technology to work, the idea is great especially since they can save a lot of money by not having to worry about a cooler. It is still crazy to me that they stuck a datacenter in the ocean, but I am glad it worked. I think Microsoft has a great idea going and I am very excited to see where the Underwater Datacenters take them in the future.
Sources
https://www.pcgamer.com/microsoft-threw-a-datacenter-into-the-ocean-and-it-worked-out-splendidly/
This is a crazy concept, and even more outrageous to actually follow through with it. I give a lot of credit to Microsoft for this. In order to demonstrate a solid execution of putting an entire container of data in the water, they need to be extremely confident in their methods of achievement. There is a lot at risk with this task. Some things I thought about that are at jeopardy regarding this project are; the reaction of water getting into the system, data being lost, sea animals around the container being injured or harmed by this, a factor of pollution, and more. I don’t know enough to say if I genuinely agree or disagree with this, however, I can definitely say this is an outside the box type of concept and I’m excited to see how this goes.
Using underwater currents, the data center may have the opportunity to be completely powered by all renewable resources. With this, energy cost savings will make these serve drastically cheaper for individuals, but more importantly, we can help save the environment. A majority of electricity in the United States is sourced from fossil fuels; AWS is striving to make its operations include “100% renewable energy usage for [their] global infrastructure.” While Amazon is not quite fully renewable yet, they are making strives, just like Microsoft is. Even besides creating solar or wind farms, which will drive up real estate and require many individuals to operate and maintain, the lower failure rate of the underwater data center can help reduce server repair costs. By harnessing underwater currents as a source of energy, these data centers can be fully operational without any fossil fuels, human intervention, or take up valuable land. This is a win-win for everyone in society.
According to a Business Insider Quote from Microsoft: “all parts of the vessel and servers will be recycled, and the ocean floor is being restored to the way it was before the project began.”
To me, this indicates that underwater data centers are a safe, sophisticated move for a healthy future and that they offer real solutions that don’t create secondary issues.
Sources: https://aws.amazon.com/about-aws/sustainability/
https://www.businessinsider.com/microsoft-project-natick-shipping-container-data-center-retrieval-in-photos-2020-9
Hearing about this really baffles my mind that Microsoft put a data center underwater. The idea of submerging servers and equipment such as that sounds so odd at first. However, it does make a lot of sense to try and see if it is feasible. The water would act as a heat sync to the data center and keep it cool without exorbitant energy costs. I did not realize what went into keeping a data center running, between the replacement parts and people bumping or jostling the servers, breaking things. Reading through the article sounded quite interesting in terms of sustainability as well as useability. These can be put near high-population areas close to the sea and feed fast data to the surrounding areas while not costing as much. Having these close to high population areas allows for “fast and smooth web surfing, video streaming and game playing.” (news.microsoft.com) While being incredibly useful, they can run off of sustainable power and not suck up as much energy from the grid. All of this is now making me realize the potential for this and I definitely would not mind faster and more reliable internet connections.
Source: https://news.microsoft.com/innovation-stories/project-natick-underwater-datacenter/
This creation of underwater data centers blows my mind because it is so modern and developed. Microsoft details how, “On land, corrosion from oxygen and humidity, temperature fluctuations and bumps and jostles from people who replace broken components are all variables that can contribute to equipment failure.” These are factors that I really never knew could influence this equipment to malfunction. A sealed container on the ocean floor could provide ways to improve the overall reliability of these underwater data centers. This idea is more elaborate, however, it is more practical and will preserve more energy.
Source: https://news.microsoft.com/innovation-stories/project-natick-underwater-datacenter/