Edge Computing

Edge Computing

                                                                                                Source: Google

Edge computing is a part of a distributed computing topology in which information processing is located close to the edge – where things and people produce or consume that information.

Basically it brings computation and data storage closer to the devices where it is being gathered , rather than relying on a central location that can be thousands of miles away. This is done so that data, especially real-time data, does not suffer latency issues that can affect an application’s performance. In addition, companies can save money by having the processing done locally, reducing the amount of data that needs to be processed in a centralized or cloud-based location.

Edge computing was developed due to the exponential growth of IoT devices, which connect to the internet for either receiving information from the cloud or delivering data back to the cloud. And many IoT devices generate enormous amounts of data during the course of their operations.

How it works ?

It basically works as a gateway which will  analyze every single bit of data that is formed by different IOT devices. After the analyzation it sends the data to the data center or cloud.

Let’s take an example- suppose we have a smart video door bell in our house that sends us live footage from our door if anyone comes. And also we have installed multiple smart door bells in our factory. Then it will be easier for a single door bell which is at our home to transmit data over the network quite easily but in case of multiple door bells in our factory transmition of data will be difficult as there are multiple IOT devices and the footage quality will suffer due to latency and tremendous costs on bandwidths.

Here edge computing hardware and services will help us  to solve this kind of problem by being a local source of processing and storage for many of these systems. An edge gateway will help us to send only the relevant data back through the cloud reducing bandwidth needs or  it can also send data back to the edge device in case of real time application needs.

Importance of edge computing

Benefits of edge computing -

1.     Data-stream acceleration, including real-time data processing without latency.

2.     Smart applications and devices respond to data immediately with no lag.

3.     Processing of large amounts of data near the source.

4.     Reduced internet bandwidth usage eliminating cost.

5.     Data processing without placing it into a public cloud.

6.     Improved customer experiences.

Many companies rely on cloud to store huge amount of data which are generated by there different applications. It costs so much bandwidth to the companies than they expected.

But edge computing has the ability to process and store data faster, enabling for more efficient real-time applications that are critical to companies. Before edge computing, a smartphone scanning a person’s face for facial recognition would need to run the facial recognition algorithm through a cloud-based service, which would take a lot of time to process. With an edge computing model, the algorithm could run locally on an edge server or gateway, or even on the smartphone itself, given the increasing power of smartphones. Applications such as virtual and augmented reality, self-driving cars, smart cities and even building-automation systems require fast processing and response in which edge computing plays a vital role.

Companies such as NVIDIA have recognized the need for more processing at the edge, which is why we’re seeing new system modules that include artificial intelligence functionality built into them. AI algorithms require large amounts of processing power, which is why most of them run via cloud services. The growth of AI chipsets that can handle processing at the edge will allow for better real-time responses within applications that need instant computing.

Privacy and security

In case of security data at the edge can face some trouble as there are different devices  that might not be as secure as a centralized or cloud-based system. As the number of IoT devices grow, it’s imperative that IT understand the potential security issues around these devices, and to make sure those systems can be secured.

Requirements of different devices such as  processing power, electricity and network connectivity can have an impact on the reliability of an edge device. This makes redundancy and failover management crucial for devices that process data at the edge to ensure that the data is delivered and processed correctly when a single node goes down.

 

Applications of edge computing

5G

As we all know 5G wireless technologies are deploying all around the world which promise the benefits of high bandwidth and low latency for applications, enabling companies to go from a garden hose to a firehose with their data bandwidth. Instead of just offering the faster speeds and telling companies to continue processing data in the cloud, many carriers are working edge-computing strategies into their 5G deployments in order to offer faster real-time processing, especially for mobile devices, connected cars and self-driving cars.

Applications using 5G technology will change traffic demand patterns, providing the biggest driver for edge computing in mobile cellular networks, the firm writes. It cites low-latency applications that include IoT analytics, machine learning, virtual reality, autonomous vehicles as those that have new bandwidth and latency characteristics that will require support from edge-compute infrastructure.

It’s clear that while the initial goal for edge computing was to reduce bandwidth costs for IoT devices over long distances, the growth of real-time applications that require local processing and storage capabilities will drive the technology forward over the coming years.

Grid edge control and analytics

Smart Grids, as we now know them, essentially work by establishing two-way communication channels between power distribution infrastructure, the recipient consumers (residential households, commercial buildings, etc.) and the utility head-end. This is done by using the tried and proven wide-area network (WAN) internet protocols.

The incredible growth-rate the internet of things is experiencing has steadily poured over into the industrial side (IIoT), bringing with it numerous technologies that can seamlessly monitor, manage and control the various functions within the electric grid’s distribution infrastructure.With the accelerating movement away from fossil fuels onto distributed renewable energies (especially solar), modern power grids are strained, now tasked with embracing proven smart technologies that are capable of integrating and managing all of these distributed energy resources into existing grids, creating a harmonized and viable distribution network– a smart grid.

Edge grid computing technologies are enabling utilities with advanced real-time monitoring and analytics capabilities, generating actionable and valuable insights on distributed energy generating resources like renewables. This is something SCADA-based systems could never do, as they were designed well before the renewable and technological boom.

Oil and gas remote monitoring

Real-time Safety monitoring is of the utmost importance for critical infrastructure and utilities like oil and gas. With this safety and reliability in mind, many cutting edge IoT monitoring devices are still being developed in order to safeguard critical machinery and systems against disaster.

Modern advanced machinery uses Internet of Things sensory devices for temperature, humidity, pressure, sound, moisture and radiation. Together with the broad vision capabilities of internet protocol enabled cameras (IP cameras) and other technologies, this produces an enormous and continuous amount of data that is then combined and analyzed to provide key insights that can reliably evaluate the health of any running system.

Computing resources at the edge allow data to be analyzed, processed and delivered to end-users in real-time. Enabling control centers with access to the data as it occurs, foreseeing and preventing malfunctions in the most optimized timely manner. This is the most practical solution, as time is of the essence in these critical systems. This rings most true when dealing with critical infrastructure such as oil, gas and other energy services, any failures within certain tend to be catastrophic in nature and should always be maintained with utmost precaution and safety procedures.

Edge video orchestration

Edge video orchestration uses edge computing resources to implement a highly optimized delivery method for the widely used yet bandwidth-heavy resource– video. Instead of delivering video from a centralized core network  through all the network hops, it intelligently orchestrates, caches and distributes video files as close to the  device as possible. Think o fit as a highly efficient and specialized instance of a content download network (CDN)  just for video, right at the edge for end-users. MEC-powered video orchestration is most useful for large public venues. Sports stadiums, Concerts and other localized events rely heavily on live video streaming and analytics to create and increase revenue streams.Freshly created video clips and live streams can quickly be served to paying customers in venues through rich media processing applications running on mobile edge servers and hotspots. This lowers the service costs and avoids many quality issues arising from bottleneck situations with terabytes of heavy video traffic hitting the mobile networks. This is something 5G edge computing is designed to solve in the coming years.

Traffic Management

one of the best ways to optimize traffic management systems is by improving real-time data. Intelligent transportation systems make extensive use of edge computing technologies, especially for traffic management processes

The influx of IoT devices and massive amounts of live data necessitate pre-processing and filtering closer to the devices, before these thousands of data streams can hit the core/cloud networks.

Using edge computing the gigabytes of sensory and special data is analyzed , filtered and compressed before being transmitted on IoT edge Gateways to several systems for further use. This edge processing saves on network expenses, storage and operating costs for traffic management solutions.

Self-driving vehicles

While self drving vehicles are not yet ready for the mainstream, without edge computing techniques their viability would be many more years in the future. With the slowdown of moore’s law and overall advance computational power the onboard computers will now form a sizeable expense of autonomous vehicles.

The myriad of complex sensory technologies involved in autonomous vehicles require massive bandwidth and real-time parallel computing capabilities. Edge and distributed computing techniques increase safety, spatial awareness and interoperability with current-generation hardware.

With mobile edge computing, vehicles can exchange real-time sensory data, corroborate and improve decisions with less onboard-resources lowering the growing expense of autonomous AI systems.