The Strategic Guide to Edge Computing
FROM EDGE COMPUTING BASICS TO THE 5G EDGE
“By 2022, more than half of enterprise-generated data will be created and processed outside of data centers, and outside of cloud.”
Information takes time to get from a user to a cloud and back again. Bandwidth is expensive. Consumers don’t like to wait. Edge computing helps you satisfy your customers and create new services and business models.
Technology is changing the way we live, work and travel. Edge computing puts IT resources close to end users and Internet of Things (IoT) devices, making possible new services and applications.
This guide explains edge computing and why it matters. You’ll find everything you need to know about edge computing, how it works with cloud computing, the impact of 5G, and how to look for best-in-class edge data centers.
Edge computing is a model where information processing (data and computing) is physically located close to the things and people that produce or consume it. Close proximity makes for the best user experience (UX).
In the past, businesses looking to improve latency connected to carrier hotels in certain Tier 1 (largest population) cities. The rise of Software-Defined Networking took it a step further by branching out to more Tier 1 cities, then Tier 2 cities, and so on. This big step in network infrastructure enabled IoT devices and services to move closer to the end-user.
The edge is where your customers are.
People and devices connect to the internet at the edge. The edge encompasses the actual location of every connected device in the world.
Companies deliver computing resources to the edge in many different ways. For example, your edge might be hundreds of micro data centers in IT closets around the world. Or your edge may be colocation data centers, managed hosting providers, or private cloud hosting providers that bring your application within one to 50 miles of thousands (or millions) of consumers.
Edge computing has been a work-in-progress for decades.
1990s: Content delivery networks Edge computing can be said to have started with Akamai’s content delivery network (CDN), which delivered cached images and videos from a network of distributed servers close to end-users. CDNs made websites run faster.
Early 2000s: Peer-to-peer overlay networks Peer-to-peer (P2P) overlay networks let participating members (peers) find other members. P2P members could distribute content and balance workloads. The internet’s domain name system (DNS) is an example of a P2P overlay network.
Mid 2000s: Public clouds The first public cloud was the Elastic Compute Cloud. Amazon rented out computing and storage resources to individuals and small companies to run their own applications.
Early 2010s: Fog computing Cisco introduced fog computing, a distributed cloud brought closer to a data source, such as smart utility meters or IoT devices. Fog provided low-latency network connections with local compute to limit the volume of data that needed to be transferred to a cloud.
Today: Edge computing Edge computing is a topology, an idea for how network connectivity is arranged. Edge computing recognizes the need for decentralized computing resources close to data sources to support many user and IoT applications.
Edge computing, cloud computing, colocation, and on-premises each deliver unique benefits to hybrid environments.
There are many reasons why businesses choose edge computing.
Reason #1: To get closer to a mobile or distributed workforce
As more data is exchanged with a remote workforce, network congestion and latency can impact application performance. Edge computing improves network performance, employee productivity and customer satisfaction.
Reason #2: To process data from the Internet of Things
The proliferation of IoT devices is driving the need for compute at the edge. IoT devices can generate a lot of data but save costs by not having much on-board processing. Edge computing enables autonomous and machine learning applications and IoT microservices .
Reason #3: To support innovative products
New business models require less latency. Edge computing allows a faster response by processing data locally, instead of incurring the latency of processing in a data center hundreds of miles away. Off-loading computing to an edge data center can also allow wearables and vehicles to weigh less.
Reason #4: To engage and interact with customers
Popular consumer applications require a lot of bandwidth (e.g. video streaming services and consumer-generated video) or low latency (e.g. video chat and augmented reality). The proximity of edge computing makes these services responsive.
Reason #5: To add new capabilities in hybrid environments
Some workloads have requirements that are best served by edge computing. On-premises, colocation , cloud computing and edge computing each deliver unique benefits – allowing an enterprise to find the right fit for each application.
Edge data centers deliver the network resources demanded by today’s consumers and enterprises.
Smart cities. Smart manufacturing. Smart agriculture . When you hear “smart” these days, it often refers to a network of IoT devices – typically wireless digital sensors that will generate data that is best processed at the edge, close to the source of the data.
Edge computing can provide information processing locally and bi-directional data flow to devices, users and to clouds. As a result, enterprise edge applications can provide monitoring and threshold alerts, business intelligence, and machine-to-machine automation in enterprise applications.
Examples of enterprise edge applications:
- Machine control
- Equipment monitoring
- Patient monitoring
- Robot surgery
- Environmental monitoring
- Vision-based analytics
- Remote facility monitoring
- Security services
- Farm monitoring
- Asset tracking
- Fleet vehicle diagnostics
- Autonomous delivery
Machine-to-machine (M2M) applications will account for half of all devices and connection by 2022.
Smart homes. Cars with autopilot. Virtual reality social platforms. Mobile gaming. Edge computing can provide local compute for applications that can free up consumers’ time for leisure, keep us safe or make us more comfortable, deliver services more efficiently, and offer us bountiful ways to fill our free time.
Examples of consumer edge applications:
- Smart home automation
- Connected cars and autopilot
- Autonomous ride sharing
- In-store engagement
- Streaming video
- Multi-player gaming
- Augmented reality
- Virtual reality social platforms
- Onsite spectator entertainment
A data center within 50 miles of its users can offer a much better user experience to your customers.
Edge computing offers many advantages to enterprises. Here are five benefits of edge computing:
Milliseconds matter to users’ perceptions of performance. Physical distance is the greatest contributor to latency. Bringing your edge data center to within 50 miles of your end users can reduce latency to imperceptible levels.
Sending information back and forth takes time (alas, limited by the speed of light). Edge computing allows data to be analyzed locally, so users don’t have to wait for data to travel to and a distant cloud or data center.
Better user experience
If it takes longer than a millisecond for a site to load, customer satisfaction suffers. Edge computing can enable faster decision making and faster responses for an improved customer experience.
Edge security requires the same stringent information security controls as IT security. Edge computing can reduce the amount of sensitive data transmitted, allow data to be anonymized closer to the source to protect personally identifiable information, and limit the amount of data stored in any one location.
Network bandwidth and data storage are expensive. Analyzing the data locally and transferring less data back to a cloud can reduce bandwidth, data communication and storage costs.
60% of servers will be located in an edge data center by 2025.
Source: Bell Labs
Edge computing and cloud computing are complementary
Hyperscale public clouds help IT organizations become more agile, but they can also increase latency if the cloud servers are far away. Just because you can operate from a distant cloud data center, should you in all cases? Edge computing and direct cloud connectivity complement cloud computing.
Edge delivers distributed computing
Edge computing is a distributed form of cloud computing. Businesses are increasingly using both hyperscale data centers (centralized) and edge data centers (distributed) to support IT strategies and digital transformation.
Edge enables near-real-time feedback
Analytics need to be located close to the edge for applications where near-real-time feedback and optimization are a priority – such as autonomous vehicles and machine-to-machine applications. After all, we don’t want an internet traffic jam to result in a real-life accident.
Edge provides direct connectivity to hyperscale clouds
Some edge data centers will provide hyperscale cloud on-ramp and off-ramp services, which help to limit the distance the data travels on the internet. AWS, Azure and Google Cloud all offer direct connections.
Edge will be managed centrally
Businesses that need to deploy and manage tens, hundreds, or thousands of distributed edge data centers will achieve economies of scale by standardizing on a software-defined configuration and replicating it repeatedly, using hyperconverged infrastructure (HCI). Such a constellation of edge data centers will be remotely monitored and managed with automation platforms. IT governance also scales with this approach. Since central IT configures the components at the edge, they can ensure consistency and adherence to best practices and policies.
5G and edge computing will enable augmented reality (AR), autonomous vehicles, smart factories and smart cities.
What is 5G?
You may have heard that once 5G becomes available, the world will never be the same again. 5G is the new (fifth generation) mobile network technology standard that will deliver faster downloads, higher network reliability and connectivity to make enterprises more efficient and to give consumers more information faster.
5G lowers latency, improving end-user experiences
It’s the lower latencies of 5G that will be a game changer for autonomous vehicles, for example. The lower you can drive latencies, the more responsive the vehicle can be to local conditions. Same thing for an application running robot warehouses. And, of course, consumers want lower latency when playing a multi-player video game or live streaming a football game.
5G and multi-access edge computing (MEC) can improve public safety. Learn more.
5G speeds will increase traffic at the mobile edge
When customers have access to a 5G network, they’ll be able to get a lot more information faster – web browsers will respond faster, and emails will download quicker. 5G will enable enterprises to realize the concept of a truly mobile office for their road warriors, remote workers, and mobile workers.
In turn, data center providers will have to adjust to the influx in traffic. Network traffic will accelerate, and data centers will need higher bandwidth connectivity to serve denser, higher throughput connections. Edge data centers with 5G will provide lower latency, higher speeds and better mobile connectivity for more consumers.
Many types of data centers will serve the 5G edge
Edge data centers don’t need to be big – in fact, they may be quite small. Edge data centers take many different forms – from a rack in a full service data center, to a micro data center purpose-engineered in a shipping container, to a cabinet on a streetlight.
Each type of micro data center provides a vastly different physical environment for the electronics inside. A micro data center located on a streetlight, for example, would be limited in its ability to deliver cooling, connectivity and power services.
Explore edge computing with a trusted data center provider
Location, location, location
TierPoint is a leading provider of secure cloud and data center solutions at the edge of the internet. We have one of the largest and most geographically diversified footprints in the nation, with over 40 world-class data centers in 20 U.S. markets and 8 multi-tenant cloud pods, connected by a coast-to-coast network.
Network fabrics & interconnection
Do you have high-bandwidth applications and need high-speed connectivity within the data center? TierPoint’s data center fabric provides any-to-any high-speed connectivity. Fast, flexible interconnectivity enables the use of other advanced networking technologies and the delivery of managed services, such as disaster recovery.
Diverse connectivity options
Move to the fast lane. Our network services deliver direct connections to AWS, Azure, and Google hyperscale public clouds that bypass the internet, cross connects for redundant carrier-diverse connectivity to the internet and private lines, and high-performance managed bandwidth between our nationwide network of data centers.