There's a new buzz term, but we haven't had one in a while. And whatever you call it, something interesting is happening within the cloud world.
We're seeing more users access increasingly large datasets. Services around streaming, content delivery, and even caching are becoming very popular. But how do you deliver such large workloads efficiently to users located all over the world? Fog computing aims to take services, workloads, applications, and large amounts of data and deliver it all to the edge of the network, where it's accessible quickly, but still highly distributed.
Cisco recently joined forces with Akamai to create a truly powerful distributed computing platform. In fact, Akamai's network is one of the world's largest distributed computing platforms, responsible for serving between 15 percent and 20 percent of all web traffic. But let's look beyond this and examine the current user, cloud, and delivery model.
The modern datacenter is, literally, the home of everything. "Everything-as-a-service" is creating a future wherein IT services, applications, communications, and pretty much all business functions are delivered via cloud. This is where fog computing kicks in. The technology involves:
- Bringing the "edge" closer to the user. Content delivery is huge. With so much more emphasis on cloud computing, there is more data being pushed down to the end user. Take a look at this report from Cisco:
In its Global Cloud Index, Cisco summarizes the forecast for datacenter IP traffic growth from 2011 to 2016.
We're already in the zettabyte era, and by 2016, nearly two thirds of all datacenter traffic will be based in the cloud. With that in mind, edge computing strives to reduce the amount of bandwidth we use and lessen latency for content. By placing the information on servers closest to the user, CDNs can deliver rich content quickly.
- Creating geographical distribution. Data analytics are becoming crucial for organizations to understand both their business and their customers. With edge/fog computing, big-data and analytics can be done faster, with better results. Complex data engines no longer have to access large datasets across the WAN. Rather, they’re able to access these edge systems and essentially bring the app to the data instead of the data to the app.
- Support for mobility and "everything-as-a-service." Fog computing platforms improve user performance and drive security and privacy efforts while enhancing mobile computing.
Whether you call it fog, edge, or CDN-based computing, it has numerous applications. Big-data platforms, as we mentioned, are perfect for this kind of technology. Consumer services like Netflix also follow this model, but they're not the only ones. Facebook, Twitter, AMD, Adobe, ESPN, Blizzard, and Trend Micro (just for a few examples) all use fog computing and edge services to deliver content. As more users connect to the cloud and request data heavy in content and size, utilizing the edge for fast delivery makes a lot of sense.
What use cases can you envision for the edge? Share your insights in the comments.