I have argued before that edge computing is the secret to perfectly crisp fries. And that in itself should be proof enough that edge is indeed the future of the cloud.
But I get it. Our culinary argument easily convinces not everyone. So I wrote this post to explain how maturing technologies like 5G and cloud-native make the edge more reliable and easier to manage. We call them to edge enablers, and here are some of them:
- IoT and connected devices are unique data sources that need to be secured and registered in the cloud. Edge will reside near or on these data sources.
- Containers provide a standardized deployment environment for developers to build and package applications. Thanks to edge computing, containers can be deployed on various hardware, regardless of device capabilities, settings and configurations.
- Service and data mesh provide a way to deploy and query data and services distributed across containers and datastores across the edge. These meshes present a single interface that abstracts away the routing and management of services and data interfaces. This critical enabler makes possible bulk queries for entire populations within the edge rather than on each device.
- Software-defined networking allows users to configure the overlay networks. It also makes it easy to customize routing and bandwidth to determine how to connect edge devices and the cloud.
- 5G makes edge deployments seamless by guaranteeing the transmission of critical control messages that manage the edge. This last-mile technology connects the border to the internet backhaul and ensures that edge devices have the right configurations and software versions to do the right things.
- A digital twin is a critical enabler that organizes physical-to-digital and cloud-to-edge. The twin allows data and applications to be configured using domain terms around assets and production lines rather than database tables and message streams. Digital twins allow domain experts (rather than software engineers) to configure applications to sense, think, and act on the edge.
Four technologies that are making edge computing even more powerful
We already see these exciting applications in my work:
- XR (extended reality) presents a genuinely immersive interface for users to collaborate or work in virtualized environments. Add edge, and you get even more detailed and interactive experiences.
For example, we are already creating immersive experiences like car buying, engineering site visits or worker safety training. Thanks to using edge, people can see new views and zoom in for unparalleled granularity.
- Heterogenous hardware processes more data — faster and using less power. Using this specialized hardware on edge embeds compute efficiently within physical environments and accelerates its response.
- Privacy-preserving technology includes techniques and hardware that allow data to be analyzed without exposing its aspects. Examples include secure enclaves, homomorphic compute, federated learning, differential privacy. Data is typically encrypted when stored and transmitted. Still, privacy-preserving technology protects the information even though the compute stage, making it more useable by other business lines and partners, especially when it needs to occur on edge.
- Robotics can be configured to act based on signals and updates at the edge. We just finished an edge implementation for robot-assisted surgery. While the surgical controls happen directly on the robot, the border also coordinates with the cloud to determine which rules are deployed on the robot, what data is used, and what information is ultimately transmitted back to the cloud.
How edge computing will drive cloud computing
All these technologies point in one direction: Edge is the future of an extended cloud continuum. Here are some ways this may unfold very soon:
Extend AI and IoT: A good deal of today's computing already happens on edge in hospitals, factories and retail locations. Much of it operates on the most sensitive data and powers the most critical systems that must function reliably and safely. Edge can help drive decisions on these core systems. Any time you have an opportunity for AI and IoT tapping into these systems, there is also an opportunity for edge.
Creating these experiences requires more advanced applications, analytics and AI, best developed and managed in the cloud. This is true when edge data can and cannot be sent to the cloud, like when we might use the cloud to generate synthetic data (e.g., created by computers).
Create unique value in partner ecosystems: Controlling the edge means you control the data access at the closest point of action. Use this unique position to create differentiated services that may be used across the entire business and among partners.
Just like data centre proximity is a premium in high-frequency trading, these points at the edge can also drive the same differentiation.
Consider the car: Edge computing is of interest to the manufacturer, but also to the insurance provider, utility and energy companies, and for city planning. Look for opportunities where edge offers new data, and you can provide value to your partners.
These new edge-enabled data and services are consumed in the cloud, where they can combine with other enterprise data and applications. They will also be catalogued and managed centrally in the cloud.
Create differentiation with 5G, robotics, XR, and connected devices: Edge computing is a must for maximizing these next-generation technologies' returns. Their combinatorial effect enables new features like voice commands to your car and remote work via teleoperation. Edge allows the programmability and control we need to fold these capabilities into the business.
Developing these highly complex use cases requires more centralized compute cycles than ever to test how they work in the real world. For example, the robotics work I do with my team begins with a simulation in the cloud, thanks to AWS Robomaker. We validate much of the robotics control system, the AI system, and the simulation's fleet management. We also test for variability in lighting conditions or form factors in wholly virtualized environments proving the solution before any physical changes or purchases are made.
Edge computing is viable today
What thrills me about edge is its ability to drive so many technological leaps so quickly. It's almost the stuff of science fiction. This is why you probably think your company is not even remotely ready to think about the edge.
I'm here to tell you that it's practical today.
The enablers I mentioned in this post — IoT, XR, 5G, and others — allow you to start imagining now how edge can make your business run more efficiently, innovate faster and get more value from your ecosystem partnerships. In other words, find your crispy fries.
What you need to know about edge computing
When people talk about edge computing, you hear a lot about self-driving cars, autonomous robots, and automated retail. But my favourite example of edge computing is from a fast-food chain.
Every restaurant location runs analytics on smart kitchen equipment data to decide exactly when to put the fries in the fryer for perfect crispiness. They use edge computing to hyper-personalize these kinds of actions for each store.
The company can create a forecast in the cloud to predict how many waffle fries should be cooked per minute over a day — easy when using transactional sales data.
Delivering services quickly with a personal touch. That's what edge computing can do.
But it's at the edge where each store micro-adjusts the initial forecast with specific on-site, real-time data from their kitchen and point-of-sale systems. Using computers at the border is how they can make sure everyone's fries are crispy, whether it's a slow afternoon or a crush of families after a little league game.
Delivering services quickly with a personal touch. That's what edge computing can do.
Does edge mean the end of cloud computing? Not! Not only is cloud computing a critical component in managing the border, but edge computing is going to drive the next wave of cloud computing.
First, what is edge computing, and how is it different from cloud computing?
Edge computing is a new capability that moves computing to the edge of the network. It's closest to users and devices — and most critically, as close as possible to data sources.
By contrast, in cloud computing, data is generated or collected in many locations and then moved to the cloud, where computing is centralized. Centralized cloud computing makes it easier and cheaper to process data together and at scale. But there are times when it doesn't make sense to send data off to the cloud for processing, like in the following scenarios:
- There's no internet, or the signal is limited, like on an oil rig using a satellite connection in the middle of the ocean.
- The data can't be transferred off-site because of security concerns or privacy regulations.
- When a device needs to analyze data and make split-second decisions, like robotics surgery. In that case, even a second or two of latency means sending data to the cloud and waiting for a decision isn't an option.
Advantages of edge computing
Sometimes, clients ask me what makes edge different. The main benefit of edge computing is reducing the risk of network outages or cloud delays when highly interactive — and timely — experiences are critical. Edge enables these experiences by embedding intelligence and automation into the physical world. Think optimizing factory operations in a factory, controlling robotic surgery on a patient, or automating production in a mine.
And if super-speed and reliability are not convincing enough, I usually follow up with three more unique attributes of edge:
- Unparalleled data control: Edge is the first point where the computer taps into the data source and determines how much of the original fidelity is preserved when digitizing the analog signal. Here's where we implement what data is stored, obfuscated, summarized and routed. It's also the point where we can add controls to address data reliability, privacy and regulations.
For example, when doing facial recognition to unlock a smartphone, it's better to keep data at the edge. The AI models are trained for each user's face without these images ever leaving the device. Since data is never transferred beyond our phones, it preserves our privacy and avoids security breaches in the cloud.
- Favourable physics laws: Edge is always on and has low latency thanks to reduced network uptime, round-trip times and bandwidth constraints.
For example, my team and I implemented a visual analytics algorithm in a factory production line to find car seat manufacturing defects. As the seats moved down a production line, we deployed our low-latency deep learning inferencing models at the edge to automate defect detection in real-time. The solution keeps pace with the uptime and production line speed, which only edge computing could allow.
- Lower costs: Processing at the edge makes cloud upload and storage cheaper. Why pay for full-fidelity data when a summarized view or key insights might be all you need?
I saw the cost-saving power of edge when I worked on my first edge implementation. It was an oilfield company whose oil wells were only accessible over-the-air — some via satellite and only by helicopter.
Data storage was limited, and direct transmission of data was costly — if it was available at all. We had already been doing analytics on the oil well data, and our next step was to deploy some of these modules directly on the well.
We used edge computing to preserve data fidelity and optimize what was stored and transmitted. We could still do rich analytics and keep the most critical (and worth-the-cost) data this way.
Will edge computing replace cloud computing?
Not at all. Even with these fantastic benefits, the edge will not replace cloud computing.
For one thing, edge capacity is limited because edge reintroduces resource constraints on battery, bandwidth, storage and computing power. Not everything can run at the border, I always say.
Instead, think of edge and cloud as part of a computing continuum. Cloud sits at the centre, and acidity complements it, as it radiates out toward the "ends" of a network.
Here are three more reasons why edge will not replace cloud computing:
- Centralized, co-located cloud computing is still needed for performance and cost. Cloud's data and enterprise app gravity is already big and is poised to grow.
- Edge computing data is feeding into more AI, which in turn needs the cloud more than ever. The inference that might happen on edge starts with bringing together data for experimentation and model training. And that takes a lot of computing power. Cloud remains the best solution when we need to combine edge, enterprise and third-party data for discovery and AI model creation.
- Edge is an extension of the cloud and requires a common platform-based approach: Adding new technologies like edge to existing cloud platforms makes it much easier to manage and optimize applications.
The future is a new cloud continuum.
Cloud and edge computing are distinct but complementary. Centrally, the cloud brings data together to create new analytics and applications, distributed on edge — residing on-site or with the customer. That, in turn, generates more data that feeds back into the cloud to optimize the experience. I call that balance in a virtuous cycle.
New edge applications that create highly contextualized and personalized experiences are sure to come. It will be hard to top the crispy fries use case, though.