Understanding how Edge Computing and AI are changing technology

In today’s interconnected world, where data is generated at an unprecedented rate, traditional cloud computing faces challenges in meeting the demands of real-time applications. Edge computing steps in as a new way to handle data, promising big changes in how we use and work with information.
Edge AI, which stands for edge artificial intelligence, is a new way of using and deploying AI technologies. By moving computing and data storage closer to where the data is created—like in IoT devices, sensors, and other connected gadgets—Edge AI is set to transform many industries.
Let’s begin by understanding the basics of AI and Deep Learning before exploring the significance of the “edge” in Edge computing and join us in this article to learn all about Edge ML and discover how industry leaders are leveraging it to change the way we live and work.

What is AI?

Artificial Intelligence (AI) is the simulation of human intelligence processes by machines and programming them to mimic human abilities such as learning, analyzing, and predicting.
There are three phases in an AI Pipeline that allows for an AI to work effectively.
1. Data Management: This phase is where data scientists wrangle the extensive volumes of data and uncovers patterns and insights within them. Data wrangling is the process of transforming raw data into readily used formats with the intent to make it more valuable for analytics. It is sometimes known as data cleaning, remediation, or munging.

2. Model Training: The next phase is to train the dataset, which is used to train a model to perform a specific task. Thus, the AI is literally created when the training is complete. This phase requires a huge amount of data and takes a substantial amount of time to complete as the training experience must be rich for the model to be efficient and effective.

3. Inference: The last phase is where AI gets deployed to perform its job of solving problems it was designed to solve. It can be deployed into serves, PC, cloud, or edge devices. It processes the data gathered from phase two to understand the new data input and outputs a result according to the parameters set.

Machine Learning
A subset of AI is Machine Learning (ML), which trains a machine to solve a specific AI problem. It is the study of algorithms that allow computers to improve automatically through experience. It uses large datasets, well-researched statistical methods, and algorithms to train models to predict outcomes from any new or incoming information.

Deep Learning
Deep learning is a further subset of ML, and it uses artificial neural networks to solve an AI problem. It consists of many successive transformations of the data that are changed together from the top to bottom, and it employs an ANN with many hidden layers, big data, and high computer resources. Similar to ML, it requires large datasets to be effective. With more data, we are able to train deep learning models to be more powerful and rely less on assumptions.
Deep learning is commonly used when dealing with more complex inputs or non-tabular data such as images, text, videos, and speech.

What is Edge AI?

In the simplest terms, Edge AI refers to the use of artificial intelligence in the form of Machine Learning (ML) algorithms deploying and inferencing on edge devices.
Machine learning, a rapidly advancing field, enables computers to autonomously improve their performance on tasks by learning from data, often surpassing human capabilities.
Edge AI is the combination of Edge Computing and AI to run machine learning tasks directly on connected edge devices. Edge AI can perform a myriad of tasks such as object detection, speech recognition, fingerprint detection, fraud detection, autonomous driving, etc.

What is Edge Computing?

Edge computing refers to processing that happens where data is produced, handling, and storing data locally in an edge device. Instead of delivering back to the cloud, edge devices can gather and process data locally, such as a user’s computer, IoT device, or edge server.
Edge computing aims to reduce latency, optimize bandwidth usage, improve scalability, and enhance privacy and security by processing data closer to the source or endpoint devices. It is particularly beneficial for applications requiring real-time data analysis and rapid response times, such as IoT devices, autonomous vehicles, and industrial automation.

Edge Computing vs Cloud Computing:

In essence, both edge and cloud computing are meant to do the same things – process data, run algorithms, etc. However, the fundamental difference in edge and cloud computing is where the computing actually takes place .
Edge Computing is a distributed computing architecture that brings computing and data storage closer to the source of data. Data processing takes place at the network’s edge, adjacent to the device that generated the data, as opposed to a central location, such as a data center.
Cloud Computing is a model for delivering information technology services over the internet. Users can now access and use shared pools of reconfigurable computing resources, including as servers, storage, databases, OS, and applications, without worrying about maintaining the underlying infrastructure.

Difference between Edge Computing and Cloud Computing

Parameter Edge Computing Cloud Computing
Definition Edge Computing is a distributed computing architecture that brings computing and data storage closer to the source of data. Cloud Computing is a model for delivering information technology services over the internet.
Location of Processing Processing is done at the edge of the network, near the device that generates the data. Data Analysis and Processing are done at a central location, such as a data center.
Bandwidth Requirements Low bandwidth is required, as data is processed near the source. Higher bandwidth is required as compared to edge computing, as data must be transmitted over the network to a central location for processing.
Costs Edge Computing is more expensive, as specialized hardware and software may be required at the edge. Cloud Computing is less expensive, as users only pay for the resources they actually use.
Scalability Scalability for Edge Computing can be more challenging, as additional computing resources may need to be added at the edge. Easier, as users can quickly and easily scale up or down their computing resources based on their needs.
Use Cases Applications that require low latency and real-time decision-making, such as IoT devices, autonomous vehicles, and AR/VR systems. Applications that do not have strict latency requirements, such as web applications, email, and file storage.
Data Security Data security can be improved, as data is processed near the source and is not transmitted over the network. Data Security is more challenging, as data is transmitted over the network to a central location for processing.

Edge AI: Bringing Cloud to the Edge to Evolve IoT

With Edge AI, IoT devices are becoming smarter and more capable. They can now make decisions, predict outcomes, process complex data, and administer solutions. For instance, edge IoT devices can predict machinery failures, allowing for predictive maintenance and cost savings.
A security camera with edge AI can identify humans, count foot traffic, and even recognize faces. As machine learning advances, these capabilities are increasingly moving from the cloud to the edge, opening up many exciting possibilities.

Benefits of Edge AI:

1. Reduced Latency: By processing data locally on edge devices, Edge AI minimizes delays, making it ideal for real-time applications like autonomous vehicles, robotics, and smart manufacturing.
2. Enhanced Privacy and Security: Data processed at the edge stays local, reducing the risk of data breaches and ensuring that sensitive information remains secure.
3. Real-time Decision Making: Edge AI enables devices to make immediate decisions based on the most current data, which is crucial for applications like predictive maintenance, healthcare monitoring, and security surveillance.
4. Scalability: Deploying AI solutions at the edge allows for scalable operations across numerous devices and locations without requiring extensive cloud infrastructure.
5. Lower Bandwidth Usage: Edge AI reduces the need to send large amounts of data over networks, saving bandwidth and lowering costs.
5. Personalized User Experiences: By processing data locally, edge devices can provide more personalized and context-aware experiences, adapting to individual preferences in real-time.

Why is Edge AI Important?

While the tangible benefits of Edge AI are clear, its intrinsic impacts may be more elusive.
Edge AI Alters the Way we Live
Edge AI is making artificial intelligence a part of our everyday lives. Although AI and machine learning have been studied for many years, we’re now seeing them in real products. For example, Self-driving cars, for example, are a product of advancements in Edge AI. Slowly but surely, Edge AI is changing the way that we interact with our environment in many ways.
Edge AI Democratises Artificial Intelligence
Artificial intelligence is no longer exclusive to research institutions and wealthy corporations. Edge AI, designed to run on affordable devices, makes AI accessible for individuals to learn and develop. This also allows educators to bring AI and machine learning into classrooms tangibly, giving students hands-on experience with edge devices.
Edge AI Challenges the Way We Think
The potential of AI and machine learning is limited only by human creativity. As machine learning advances, more tasks will be automated, challenging our ideas of productivity and purpose. Though the future is uncertain, I’m optimistic that Edge AI will lead to more creative and fulfilling jobs. What are your thoughts?

Edge AI with edge GPU: NVIDIA Jetson embedded system

reComputer built with Jetson Nano/NX: real world AI at the Edge
NVIDIA® Jetson™ brings accelerated AI performance to the Edge in a power-efficient and compact form factor. The Jetson family of modules all use the same NVIDIA CUDA-X™ software, and support cloud-native technologies like containerization and orchestration to build, deploy, and manage AI at the edge
image
Product Features:

  • Edge AI box fit into anywhere
  • Embedded Jetson Nano/NX Module
  • Pre-installed Jetpack for easy deployment
  • Nearly same form factor with Jetson Developer Kits, with rich set of I/Os
  • Stackable and expandable

Edge AI with TPU: Google Coral series

Google’s Coral series is equipped with their Tensor Processing Units (TPUs), which are purpose-built ASICs designed specially for neural network machine learning with TensorFlow Lite. The Coral Dev board is an all-in-one, TPU-equipped platform that allows you to prototype TFLite applications easily, which can even be scaled to production with its flexible SoM design!
image
Product Features:

  • NXP i.MX 8M SoC (Quad Cortex-A53, Cortex-M4F) CPU
  • Integrated GC7000 Lite Graphics
  • Google Edge TPU coprocessor
  • 1 GB LPDDR4, 8GB eMMC
  • Suite of Interfaces: HDMI, MicroSD, WiFi, Gigabit Ethernet and more!

Alternatively, you might be interested in the Coral USB Accelerator, which allows you to use Google’s Edge TPU with your existing development boards via USB! For embedded applications that require more power, the Coral M.2 Accelerator with Dual Edge TPU can be used with any system via the speedy M.2 interface, and sports two Edge TPUs for some serious machine learning capabilities!

SBCs for Edge AI

Edge AI is developing rapidly, and nobody wants to miss out. Fortunately, getting started with Edge AI is easier than ever with the wide variety of edge devices available. In this section, I’d like to share a few SBC recommendations for those of you who would like to get your toes wet with Edge AI!

Intel Celeron-powered ODYSSEY X86 series

image
When it comes to general-purpose computing, you’ll be hard pressed to find anything better than the ODYSSEY x86 series. Running on the powerful x86 CPU architecture, this SBC is capable enough to meet any edge computing requirement, or even serve as a mini PC to replace your desktop.

Beginner-Friendly: Raspberry Pi 4B

image
If you’re a beginner or if you’re looking for a beginner-friendly option for your child, you most certainly won’t go wrong with the Raspberry Pi 4B. Although the popular Raspberry Pi isn’t as powerful as the other recommendations I’ve shared so far, it is still a very capable SBC for anyone who is trying to learn Edge AI or general computing.

Is Edge AI Possible on Microcontrollers?

Modern processors, capable of trillions of operations per second (TOPS), are not crucial for machine learning. Microcontrollers, some with embedded ML accelerators, are now enabling ML on edge devices. This article examines how Edge AI integrates AI into smaller, less powerful computers, including microcontrollers with minimal RAM.
TinyML, a new concept, answers these challenges by enabling ML in highly resource-constrained environments.
The goal of TinyML is to allow inferencing, and ultimately training, to be executed on small, resource-constrained low-power devices, and especially microcontrollers, rather than larger platforms or in the cloud.
This requires neural network models to be reduced in size to accommodate the comparatively modest processing, storage, and bandwidth resources of these devices, without significantly reducing functionality and accuracy.

Best Microcontrollers for Edge AI

GROVE VISION AI MODULE V2 - M55
image
The Grove - Vision AI V2 is a highly efficient MCU-based smart vision module driven by the Himax WiseEye2 HX6538 processor, featuring a dual-core Arm Cortex-M55 and integrated Arm Ethos-U55 neural network component. It integrates Arm Helium technology , which is finely optimized for vector data processiong, enables a significant uplift in DSP and ML capabilities without compromising on power consumption, which is ideal for battery-powered applications .

Seeed Studio XIAO ESP32S3 Sense: and Seeed Studio XIAO nRF52840 Sense:
Seeed Studio XIAO Series are diminutive development boards, sharing a similar hardware structure, where the size is literally thumb-sized. The code name “XIAO” here represents its half feature “Tiny”, and the other half will be “Puissant”.


Seeed Studio XIAO ESP32S3 Sense integrates an OV2640 camera sensor, digital microphone, and SD card support. Combining embedded ML computing power and photography capability, this development board can be your great tool to get started with intelligent voice and vision AI.

Seeed Studio XIAO nRF52840 Sense is carrying Bluetooth 5.0 wireless capability and is able to operate with low power consumption. Featuring onboard IMU and PDM, it can be your best tool for embedded Machine Learning projects.

Wio Terminal:
image

The Wio Terminal is a complete Arduino development platform based on the ATSAMD51, with wireless connectivity powered by Realtek RTL8720DN. As an all-in-one microcontroller, it has an onboard 2.4” LCD Display, IMU, microphone, buzzer, microSD card slot, light sensor & infrared emitter. The Wio Terminal is officially supported by Edge Impulse, which means that you can easily use it to collect data, train your machine learning model, and finally deploy an optimized ML application!

Conclusion:

In today’s data-driven world, traditional cloud computing struggles with real-time demands. Edge computing and Edge AI are transforming data handling by deploying AI closer to where it’s needed, revolutionizing industries. This shift enhances efficiency, reduces latency, and empowers IoT devices to make autonomous decisions. As Edge AI advances, it promises a future where smart solutions at the edge drive innovation, security, and scalability, integrating AI more deeply into daily life. Embrace the evolution of Edge AI and computing to harness intelligent solutions for our interconnected world.

Applicable Part Numbers
Manufacturer Part Number Digikey Part Number
110061362 1597-110061362-ND
110061361 1597-110061361-ND
102110297 1597-102110297-ND
113990660 1597-113990660-ND
102110260 1597-102110260-ND
114991790 1597-114991790-ND
102110449 1597-102110449-ND
102110539 1597-102110539-ND
102110767 1597-102110767-ND
102110301 1597-102110767-ND
113991115 1597-113991115-ND
102010469 1597-102010469-ND
102991299 1597-102991299-ND