In this article:
- What Is Edge Computing?
- How Does Edge Computing Work?
- What is Bandwidth ?
- What is Latency ?
- Why Is Edge Computing Needed?
- What Are the Benefits of Edge Computing?
- What Are the Main Applications of Edge Computing?
- Applications for Edge AI
- NVIDIA at the Edge
- The Does the Future of Edge Computing Hold ?
What Is Edge Computing?
Edge computing is the practice of processing data physically closer to its source.
In a nut shell… moving compute power physically closer to where the data is generated – to the “edge” of a device or network.
Many innovative technologies are made possible thanks to edge computing, such as Smart cities, remote surgeries, fully autonomous vehicles and voice-controlled home speakers.
Data can be processed faster with increases in available bandwidth and ensures data sovereignty, when incorporating ‘Edge’ Computing.
The need for large amounts of data travelling between servers, the cloud and edge locations, is reduced and issues such as latency and available bandwidth found in conventional data processing are all be it resolved.
Having these issues resolved are important for modern applications such as data science and AI.
For example, AI-capable processors that can infer at the edge, power intelligent sensors within most advanced industrial equipment.
This is known as Edge AI.
Supervisors within such a factory setting can be alerted of any anomalies that potentially jeopardize safe, continuous and effective operations, as the sensors monitor equipment and nearby machinery.
In this case, with AI processors physically present at the industrial site results in lower latency and the industrial equipment reacting more quickly to their environment.
Where human safety is a factor, such as with self-driving cars, the instantaneous feedback that edge computing offers is especially critical for such applications, where saving even milliseconds of data processing and response times can be key to avoiding accidents.
Edge computing can be used everywhere sensors collect data — from retail stores for self-checkout and hospitals for remote surgeries, to warehouses with intelligent supply-chain logistics and factories with quality control inspections.
How Does Edge Computing Work?
Where data produced by sensors, was once either manually reviewed by humans, left unprocessed or sent to the cloud or a data centre for processing and then sent back to the device, data is often now processed as close to its source or end user as possible.
The centralised network or data centre is now kept away from the data, applications and computing power.
Relying solely on manual reviews results in slower, less efficient processes. Cloud computing provides computing resources, however, data travel and processing puts a large strain on bandwidth and latency.
What is Bandwidth ?
Bandwidth is the rate at which data is transferred over the internet. When data is sent to the cloud, it travels through a wide area network, which can be costly due to its global coverage and high bandwidth needs. When processing data at the edge, local area networks can be utilized, resulting in higher bandwidth at lower costs.
What is Latency ?
Latency is the delay in sending information from one point to the next. Latency is reduced when processing at the edge, because data produced by sensors and IoT devices no longer needs to send data to a centralised cloud, to be processed.
Even on the zippiest fibre-optic networks, data can’t travel faster than the speed of light.
In order to reduce bottlenecks and accelerate applications, edge computing can be run on one, or multiple systems, to close the distance between where data is collected and processed.
Within an ideal edge infrastructure, a centralised software platform that can remotely manage all edge systems in one interface, will be involved.
Why Is Edge Computing Needed?
The three technology trends IoT, AI and 5G, are converging and are creating use cases that are requiring organisations to consider edge computing.
With the proliferation of IoT devices came the explosion of big data that businesses started to generate.
These businesses soon realised that their applications were not built to handle the large volumes of data that they were now wanting to collect.
They also realised that the infrastructure for transferring, storing and processing large volumes of data can be expensive and difficult to manage. That may be why only a fraction of data collected from IoT devices is ever processed, in some situations it is as low as 25 percent.
And the problem is compounding. There are 40 billion IoT devices today and predictions from ARM show that there could be 1 trillion IoT devices by 2022, so as the number of IoT devices grows and the amount of data that needs to be transferred, stored and processed, increases, organisations are shifting to edge computing to alleviate the costs required in order for them to be able to use the same data in cloud computing models.
AI (Artificial Intelligence)
Similar to IoT, AI represents endless possibilities and benefits for businesses, such as the ability to glean real-time insights. Just as quickly as organizations are finding new use cases for AI, they’re discovering that those new use cases have requirements that their current cloud infrastructure can’t fulfill.
When organizations have bandwidth and latency infrastructure constraints, they have to cut corners on the amount of data they feed their models. This results in weaker models.
5G networks clock in at approximately 10x faster than 4G ones and built to allow each node to serve hundreds of devices, which has increased the possibilities for AI-enabled services at edge locations.
As edge computing is powerful, quick and offers reliable processing power, businesses have the potential to explore new business opportunities, gain real-time insights, increase operational efficiency and improve their user experience.
What Are the Benefits of Edge Computing?
The main benefits of edge computing are:
- Lower Latency Data travel is reduced, by processing data at a network’s edge, accelerating AI making more complex AI models that require low latency, such as fully autonomous vehicles and augmented reality, now possible.
- Reduced Cost Higher bandwidth and storage at lower costs, compared to cloud computing, can now be accessed by organisations by using LAN for data processing and because processing happens at the edge, less data needs to be sent to the cloud or data centre for further processing and which also results in a decrease in the volume of data that needs to travel, which reduces costs even further.
- Model Accuracy AI relies on high-accuracy models, particularly for edge use cases that require instantaneous responses. When a network’s bandwidth is too low, it’s typically mitigated by reducing the size of data used for inferencing. This results in reduced image sizes, skipped frames in video and reduced sample rates in audio. When deployed at the edge, data feedback loops can be used to improve AI model accuracy and multiple models can be run simultaneously resulting in improved insights.
- Wider Reach Traditional cloud computing requires internet access, whereas edge computing can process data without internet access, meaning its range of uses, can be extended to remote or previously inaccessible locations.
- Data Sovereignty Edge computing allows organisations to keep all of their data and compute inside the LAN and company firewall. This results in reduced exposure to cybersecurity attacks in the cloud and strict and ever-changing data laws.
What Are the Main Applications of Edge Computing?
Edge Computing for Retail
The world’s largest retailers now enlist Edge AI to deliver better experiences for customers.
With edge computing, retailers can boost their agility by:
- Reducing shrinkage Stores can identify and prevent instances of errors, waste, damage and theft, via in-store cameras and sensors, as Edge AI can be leveraged to analyze relevant data.
- Improving inventory management Edge computing applications can use also in-store cameras to alert store associates when shelf inventories are low, reducing the impact of stockouts.
- Streamlining shopping experiences Retailers can now implement voice ordering so shoppers can easily search for items, ask for product information and place online orders using smart speakers or other intelligent mobile devices, thanks to the fast data processing that edge computing now brings to the retail space.
Edge Computing for Smart Cities
Many places have started to use AI at the edge, transforming them into smart spaces. Cities, university campuses, stadiums, shopping centres, and other entities are using AI to make their opertations more efficient, safe and accessible.
Edge computing has been used to transform operations and improve safety around the world in areas such as:
- Reducing traffic congestion Computer vision is used to identify, analyze and optimize traffic. Cities use its offering to improve traffic flow, decrease traffic congestion-related costs and minimise the time drivers spend in traffic.
- Monitoring beach safety SightBit’s image-detection application helps spot dangers at beaches, such as rip currents and hazardous ocean conditions, allowing the authorities to enact life-saving procedures.
- Increasing airline and airport operation efficiency Assaia International AG created an AI-enabled video analytics application to help airlines and airports make better, more informed and quicker decisions around capacity, sustainability and safety.
Edge Computing for Automakers and Manufacturers
Sensor data generated by factories, manufacturers and automakers can now be used in a cross-referenced fashion to improve services.
Some popular use cases for promoting efficiency and productivity in manufacturing include:
- Predictive maintenance In order to avoid downtime when machines fail, edge computing can be used to detect any anomalies early in the system.
- Quality control Edge computing can also assist with the detection of any defects within products and to alert staff in an instance, which in turn helps to reduce waste and to make the manufacturing of such products more efficient.
- Worker safety Using a network of cameras and sensors equipped with AI-enabled video can allow manufacturers to identify workers that are in unsafe conditions and intervene to prevent accidents.
Edge Computing for Healthcare
Healthcare is currently being helped to reshape by the combination of edge computing and AI.
In order to make operations more efficient, ensure the safety of the patients and staff, whilst providing the highest-quality of care possible, Edge AI has been deployed to provide healthcare workers the tools they need.
Two popular examples of AI-powered edge computing within the healthcare sector are:
- Operating rooms AI models built on streaming images and sensors in medical devices are helping with image acquisition and reconstruction, workflow optimisations for diagnosis and therapy planning, measurements of organs and tumours, surgical therapy guidance and real-time visualisation and monitoring during surgeries.
- Hospitals Patient monitoring, patient screening, conversational AI, heart rate estimation, radiology scanners, are just some of the technologies being used within Smart Hospitals. Human pose estimation is a popular computer vision task, that estimates key points on a person’s body such as eyes, arms and legs, by helping to notify staff when a patient moves or falls out of a hospital bed.
Applications for Edge AI
To complement these offerings, NVIDIA has also worked with partners to create a whole ecosystem of software development kits, applications and industry frameworks in all areas of accelerated computing.
This software can be remotely deployed and managed using the NVIDIA NGC software hub. AI and IT teams can get easy access to a wide variety of pretrained AI models and Kubernetes-ready Helm charts to implement into their edge AI systems.
NVIDIA at the Edge
The ability to glean faster insights can mean saving time, costs and even lives. That’s why enterprises are tapping into the data generated from the billions of IoT sensors found in retail stores, on city streets and in hospitals to create smart spaces.
To do this, organisations need edge computing systems that deliver powerful, distributed compute, secure and simple remote management, and compatibility with industry-leading technologies.
NVIDIA, one of the leading manufacturers of such technologies, brings together NVIDIA-Certified Systems, embedded platforms, AI software and management services, that allow enterprises to harness the power of AI at the edge.
The Does the Future of Edge Computing Hold ?
According to past market research the edge computing market is on target to be worth $251 billion by 2025 and is expected to continue growing each year with a compounded annual growth rate of 16.4 percent.
The evolution of AI, IoT and 5G will continue to catalyse the adoption of edge computing with the number of use cases and the types of workloads deployed at the edge continuing to grow.
Today, the most prevalent edge use cases revolve around computer vision. However, there are many untapped opportunities in workload areas such as natural language processing, recommender systems and robotics.
The possibilities at the edge are limitless.