9 killer apps for edge computing

Edge computing provides a new paradigm for running applications on platforms outside the cloud. The edge is where users and their devices come into contact with the network that connects them. It is a platform, but a platform without applications is like a hammer without a nail. So what is the real killer application for edge computing?

[[260563]]

1. IoT Gateway

Edge computing and the Internet of Things (IoT) go hand in hand. With the explosion of new connected devices, everything from cars to toasters now has an IP address. These new devices are generating a lot of data. So much data that your limited internet uplink can't keep up.

By processing most of the data in edge devices in IoT gateways close to the source rather than in the cloud, connected devices can consume less backhaul bandwidth. If the uplink fails, the IoT gateway can continue to operate, so you are not plunged into darkness when your connected switches and connected light bulbs temporarily lose connection to the cloud.

The Industrial Internet of Things (IIoT) elevates these concepts to an industrial scale. Many existing industrial devices expose data to being ignored or lost over time (as much as 97%, in fact). By collecting and rationalizing this data at the Edge, Industrial IoT gateways can improve the efficiency and effectiveness of industrial automation.

IoT and IIoT can also serve as a platform for several related Edge Computing applications, including connected cars, transportation, and energy. These applications share remote sensing analysis and edge-locally driven IoT capabilities.

2. Network Functionality

Routers, switches, and firewalls usually conjure up images of big metal boxes. While network functions have traditionally run on dedicated appliances, network function virtualization (NFV) has taken these closed systems and transformed them into software that can run in virtual machines or even Docker containers. Unlike the other applications discussed in this article, network functions must run at the edge. Packet forwarding and security functions cannot be outsourced to the cloud while maintaining real-time performance.

Fortunately, the combination of NFV and Edge Computing makes it simple to manage the lifecycle and configuration of these new virtualized network functions. Network service providers are already considering turning to NFV as an opportunity to launch general-purpose edge computing platforms such as multi-access/mobile edge computing (MEC).

3. Games

Multiplayer gaming is a bandwidth-intensive and latency-sensitive application. By matching gamers based on location and then placing game servers closer to them, multiplayer network latency can be reduced to single-digit milliseconds. The lower the latency between a console or PC gaming rig and the backend servers, the lower the lag. The rise of competitive gaming shows that a large gaming community is willing to pay a premium for a better experience.

With edge computing, services like cloud gaming become feasible. Instead of investing in a new PC, PlayStation, or Xbox every year or two, gamers can subscribe to a hosted gaming service. Edge computing hardware is kept up to date and users can connect remotely. While previous attempts at cloud gaming (such as OnLive) failed due to real-time latency issues, the development of managed edge computing platforms may reignite this model, leveraging the release of Google's Stadia and Microsoft's xCloud.

4. Content Delivery

The original Edge Computing application. By caching content at the edge - whether it's a web page, video or music - end users can enjoy a better experience. Edge caching provides a huge improvement over traditional web servers, providing about one millisecond of latency.

This was news 20 years ago; how does it relate to Edge Computing today? The content delivery network (CDN) market has been dominated by a few players, such as BAT’s CDN services, Akamai, and Limelight. They have built a massive global cache network. What if the Edge looked more like the cloud? Instead of relying on a CDN provider, any content provider (such as HBO or Netflix) can launch their own custom micro-cache at the edge of the network, giving them more flexibility and customization than using a general-purpose CDN provider.

5. Machine Learning for Speech and Video Recognition

Voice recognition through Alexa, Google Assistant, and Siri is now mainstream. And, in a world where devices are increasingly connected, the number of voice- and video-enabled devices will only increase. Pulling all this voice and video content back to the cloud is expensive. Users expect low-latency responsiveness without affecting their data plans.

Edge Computing enables the execution of machine learning inference models, such as those used for voice and video analytics, closer to end users and their devices than ever before. By converting speech to text at the Edge, megabytes (MB) of voice recordings can be converted into just a few bytes of text.

6. Virtual Desktop

While cloud software is the future of enterprise applications, many people still rely on virtual desktops to get their work done. Whether these virtual desktop environments are hosted in a corporate data center or run in a public cloud, they can be slow for remote workers and can even halt productivity under the wrong network conditions.

Edge Computing has the potential to free virtual desktop environments from the data center and provide remote workers with highly controlled localized access through virtual machine migration. Imagine using a virtual desktop environment in the office and then having the virtual desktop instance follow you to the nearest Edge site. As with the gaming use case, lower latency will have a significant impact.

7. Video Conferencing

Whether you attend meetings every day or once a quarter, most of us have experienced conferencing software, but voice delays, poor video quality, and frozen screen shares are not uncommon. These problems can be caused by a slow link to the cloud, where multiple voice and video streams are multiplexed together.

By placing the server side of voice and video conferencing software closer to the participants, these types of quality issues can be significantly reduced. A globally distributed voice and video server Edge architecture provides a more resilient and responsive user experience for conference participants.

8. Cloud Storage

Everyone has data in the cloud, but sometimes it can be hard to access. It can be slow or even unusable. Whether you use services like Dropbox and Google Drive, or just try to access a Network File System (NFS) over the internet, remote storage doesn't always work the way it should.

Edge Computing can help solve this problem. By placing a storage gateway at the edge of the Edge, the gateway can act as a read/write cache. If a cloud storage service is unavailable, it can provide a locally cached set of working files. On slow connections, it can provide the appearance of a fast local storage array despite an abnormally slow uplink.

9. Augmented Reality

Gorgeous Edge Use Cases. In reality, augmented reality (AR) is unlikely to be the driving factor for edge computing moving forward. While edge computing can reduce the need for computing power in lightweight AR headsets, power trade-offs and the current reliance on specialized hardware make it difficult to use AR as an application for current general-purpose edge computing platforms. However, AR definitely fits the pattern of the archetypal edge computing application: bandwidth-hungry and latency-sensitive. As this technology advances, augmented reality will undoubtedly benefit from the development of edge computing and make great strides forward.

No single application alone will be enough to drive the emergence of a universal edge computing platform. However, these applications can create an ecosystem of platforms around the edge that can handle heterogeneous workloads while enabling new possibilities that have not yet been imagined.