Windows 10: Bringing intelligence to the edge with Google Cloud IoT Edge

Brink · Jul 25, 2018

The internet of things (IoT) presents us with enormous opportunities to positively affect the world around us—everything from increasing air quality to easing traffic to saving water and electricity. We can measure the world in new ways that can impact lives for the better.

But just as opportunities increase with IoT, so does data. IDC estimates that the total amount of data generated from connected devices will exceed 40 trillion gigabytes by 2025. This is where advanced data analytics and AI systems can help, to extract insights from all that data quickly and easily.

There are also many benefits to be gained from intelligent, real-time decision-making at the point where these devices connect to the network—what’s known as the “edge.” Manufacturing companies can detect anomalies in high-velocity assembly lines in real time. Retailers can receive alerts as soon as a shelved item is out of stock. Automotive companies can increase safety through intelligent technologies like collision avoidance, traffic routing, and eyes-off-the-road detection systems.

But real-time decision-making in IoT systems is still challenging due to cost, form factor limitations, latency, power consumption, and other considerations. We want to change that.

Bringing machine learning to the edge

Today, we’re announcing two new products aimed at helping customers develop and deploy intelligent connected devices at scale: Edge TPU, a new hardware chip, and Cloud IoT Edge, a software stack that extends Google Cloud’s powerful AI capability to gateways and connected devices. This lets you build and train ML models in the cloud, then run those models on the Cloud IoT Edge device through the power of the Edge TPU hardware accelerator.

Edge TPU is Google’s purpose-built ASIC chip designed to run TensorFlow Lite ML models at the edge. When designing Edge TPU, we were hyperfocused on optimizing for “performance per watt” and “performance per dollar” within a small footprint. Edge TPUs are designed to complement our Cloud TPU offering, so you can accelerate ML training in the cloud, then have lightning-fast ML inference at the edge. Your sensors become more than data collectors—they make local, real-time, intelligent decisions.

The Edge TPU chip, shown with a standard U.S. penny for reference

Cloud IoT Edge is the software that extends Google Cloud’s powerful data processing and machine learning capabilities to gateways, cameras, and end devices, making IoT applications smarter, more secure and more reliable. It lets you execute ML models trained in Google Cloud on the Edge TPU or on GPU- and CPU-based accelerators. Cloud IoT Edge can run on Android Things or Linux OS-based devices, and its key components are:

A runtime for gateway class devices, with at least one CPU, to locally store, translate, process, and derive intelligence from data at the edge, while seamlessly interoperating with the rest of Cloud IoT platform.

The Edge IoT Core runtime that more securely connects edge devices to the cloud, enabling software and firmware updates and managing the exchange of data with Cloud IoT Core.

The TensorFlow Lite-based Edge ML runtime that performs local ML inference using pre-trained models, significantly reducing latency and increasing the versatility of edge devices. Because the Edge ML runtime interfaces with TensorFlow Lite, it can execute ML inference on a CPU, GPU or an Edge TPU in a gateway class device, or in an end device such as a camera.

How machine learning at the edge benefits businesses

Businesses can benefit by bringing machine learning to the edge in several different ways.

Increased operational reliability

Because you can locally store, process, and derive intelligence from data at the edge, you can build robust IoT solutions on-premise, without worrying about intermittent cloud connectivity. This can be helpful for video and audio applications that require real-time processing, or use cases where devices can’t reliably connect to an external network or the internet.

Faster real-time predictions

By running on-device machine learning models, Cloud IoT Edge with Edge TPU provides significantly faster predictions for critical IoT applications than general-purpose IoT gateways—all while ensuring data privacy and confidentiality. Plus, Cloud IoT Edge and Edge TPU have been extensively tested to natively run open source reference models like MobileNet and Inception V3.

Increased security for devices and data

Cloud IoT Edge can process and analyze images, videos, gestures, acoustics, and motion locally on edge devices, instead of needing to send raw data to the cloud and then wait for a response. This local processing addresses certain industry-specific compliance needs and reduces data privacy risks. And Cloud IoT Edge uses a JSON Web Token to authenticate edge devices so that the private key never leaves the device.

Introducing the Edge TPU development kit

To jump-start development and testing with the Edge TPU, we’ve built a development kit. This kit includes a system on module (SOM) that combines Google’s Edge TPU, a NXP CPU, Wi-Fi, and Microchip’s secure element in a compact form factor. It’ll will be available to developers this October. To request early access to the Edge TPU development kit, sign up via this form.

The Edge TPU development kit—SOM (above) and base board (below)

We’re also working with our IoT ecosystem partners to develop intelligent devices that take advantage of Google Cloud IoT innovations at the edge. Semiconductor partners will create the SOM with the Edge TPU chip inside. Device makers will make industrial IoT gateways—like the kind used in factories, locomotives, oil rigs, and more—that include the SOM and Edge TPU.
Partners we're working with include:

Semiconductor companies: NXP, ARM

Gateway device makers: Accton, Harting, Hitachi Vantara, Nexcom, Nokia

Edge computing: ADLINK Technology, Kelvin, Olea Edge Analytics, Smart Catch, Trax

What our customers are saying

“Our Intelligent Vision Inspection solution enables us to deliver enhanced quality and efficiency in the factory operations of various LG manufacturing divisions. With Google Cloud AI, Google Cloud IoT Edge, and Edge TPU, combined with our conventional MES systems and years of experience, we believe Smart Factory will become increasingly more intelligent and connected,” says Shingyoon Hyun, the CTO of LG CNS. “With Intelligent Vision Inspection, we are eager to make a better working place, raise the quality of product, and save millions of dollars each year. Google Cloud AI and IoT technologies with LG CNS expertise make this possible.”

"Smart Parking enables our customers to deploy and manage frictionless parking services for both on-street and off-street situations. We are very excited about our ability to use Cloud IoT Edge and Edge TPU for building ML-enabled parking experiences for our customers,” says John Heard, CTO of Smart Parking. “At Smart Parking, our mission is to re-invent the parking experience for every solution user. The introduction of Cloud IoT Edge, Google Cloud IoT enables us to deliver on this promise in new ways within our SmartSpot gateway products.”

“At XEE, we’re working to make driving simpler, safer and more economical through our connected car platform,” explains Romain Crunelle, CTO at XEE. “Cloud IoT Edge and Edge TPU will help us to address use cases such as driving analysis, road condition analysis, and tire wear and tear in real time and in a much more cost efficient and reliable way. Enabling accelerated ML inference at the edge will enable the XEE platform to analyze images and radar data faster from the connected cars, detect potential driving hazards and alert drivers with real-time precision."

"Trax is helping retailers build a sound foundation for digital transformation,” says David Gottlieb, General Manager, Global Retail at Trax. “Cloud IoT Edge and Edge TPU will help address critical use cases such as improving on shelf availability (OSA), optimizing click-and-collect processes, and modernizing the shopping experience. This Google technology will enable accelerated machine learning at the edge—in-store images are captured and flowed through the Trax platform, where those digitized shelf images are analyzed at an increasingly faster rate providing retailers with the agility to both respond to issues in real time and to consistently delight shoppers.”

Getting started

Cloud IoT Edge, Edge TPU and Cloud IoT Core are opening up completely new possibilities with IoT. With powerful data processing and ML capabilities at the edge, devices such as robotic arms, wind turbines and smart cars can now act on the data from their sensors in real time and predict outcomes locally. For IoT, this is the future—and we can’t wait to see what you build with Google Cloud IoT.
Click to expand...

Source: Bringing intelligence to the edge with Cloud IoT

:)

Brink · Jul 25, 2018

Do more at the intelligent edge with Windows 10 IoT

Microsoft announces the Windows AI Platform with Windows 10 IoT, Azure Machine Learning, and Azure IoT Edge to accelerate the intelligent edge.

In the world of connected things, devices are getting more powerful. Advances in silicon, memory, and cloud technologies including machine learning and artificial intelligence are enabling devices to do more at the edge. These advances will expand use cases in manufacturing, healthcare, agriculture, and many other industries where an intelligent edge will unlock the power of the intelligent cloud in new ways.
Today, we are excited to announce a Windows AI Platform-enabled solution to put this power in the hands of every developer. In the next update to Windows 10, the Windows AI Platform with Azure Machine Learning together with Azure IoT Edge will bring hardware-accelerated machine learning model evaluation on the edge. By using instruction set optimizations on modern CPUs, hardware acceleration on GPUs that support DirectX 12, and a driver model for purpose-built AI processors in the future, the Windows AI Platform will deliver performance and efficiency on the broadest range of form factors.
At Microsoft Build 2018, we are showcasing this through a powerful demonstration. Imagine a production line in a steel factory equipped with cameras that can capture every square inch of steel passing through the line. Using traditional image processing techniques, it’s difficult to process and analyze this information, derive insights, and take actions in a timely and affordable manner. Using the Windows AI Platform available on every Windows 10 device, the machine learning model on the device will process the images at the edge and can detect anomalies on the steel surface instantaneously. With Azure IoT Edge, the device can be configured to send alerts or take a corrective action. With Azure Machine Learning, the ML model will be retrained and redeployed easily and quickly across devices. Such a deployment will enable a truly intelligent edge with hardware that is already available in market on a Windows 10 device with Direct X12 GPU.

Windows AI Platform powering edge solution at a steel factory.

At EmbeddedWorld2018, Microsoft announced 10 years of security updates and an expanded offering of long-life silicon for Windows 10 IoT Core. In close collaboration with NXP, we have begun a private preview of Windows 10 IoT Core on NXP i.MX 6 and i.MX 7 processors. Today, we are announcing that Microsoft and NXP will release commercial support for IoT Core with i.MX6 and i.MX7 with the next release of IoT Core.

Windows 10 IoT platform continues to evolve with feature investments including the Windows AI Platform, expanded silicon offerings, and long-term support commitment. We are excited about the possibilities and want to see what you do with this. To learn more about developing with Windows 10 IoT, enroll in our Early Adopter Program at L: EEAPIOTPartner@microsoft.com.
Click to expand...

Source: Do more at the intelligent edge with Windows 10 IoT - Windows Experience Blog

See also: Unlocking the IoT promise - from the intelligent cloud to the intelligent edge - Internet of Things

Chino · Jul 25, 2018

SolidRun's MACCHIATObin ClearCloud 8K Comes with Google Cloud IoT Core Support

SolidRun, a leading developer and manufacturer of high-performance embedded solutions, and edge computing platforms, today announced support for the public beta of Google Cloud IoT Core, a fully managed service on Google Cloud Platform (GCP) to securely connect and manage IoT devices at scale. Cloud IoT Core is now publicly available to all users in beta, including new features and pricing plan. With Cloud IoT Core, businesses can easily connect and centrally manage millions of globally dispersed IoT devices. When used as part of the broader Google Cloud IoT solution, it can ingest all IoT data and connect to Google Cloud's state of the art analytics services including Cloud Pub/Sub, Dataflow, Bigtable, BigQuery, and Machine Learning.

The MACCHIATObin ClearCloud 8K, is based on a Marvell ARMADA A8040 SoC, and features a quad core Arm Cortex A-72 1.6GHz processor, including 4GB DDR4 DIMM memory (16GB optional), dual 10GbE, microSD connectors, 3 x SATA 3.0, USB 3.0 and PCIe x4 3.0 slot. SolidRun's MACCHIATObin ClearCloud 8K with Google's Cloud IoT Core allows users to easily and securely connect to GCP. The solution has been developed in collaboration with Sartura Ltd., a leading specialized open source developer and integrator for embedded applications, in conjunction with Marvell.

"It is only natural that a leading edge computing and gateway solution provider like SolidRun will complement its offering with an easy access to cloud services such as Google Cloud Platform," says Dr. Atai Ziv, SolidRun's CEO.

"With the MACCHIATObin ClearCloud 8K broadly available to customers on IoT Core, customers can gain visibility into new operational data and optimize for change in real-time," said Adam Massey, Director, Strategic Technology Partners, Google Cloud. "Together with SolidRun, we are striving to make it easier to connect, manage, and drive real business value from IOT devices."

MACCHIATObin ClearCloud 8K comes with a unique fanless GCP enclosure, and accessories for a price tag of $399.

Brink · Jul 25, 2018

Cloud plus artificial intelligence is creating The Matrix

The Matrix is coming, but it might not look quite how you might expect.

A study by advisory firm Leading Edge Forum titled Embracing 'the Matrix' and the Machine Intelligence Era, suggests that the combination of cloud computing and artificial and machine intelligence (MI) "will increasingly be able to perform just about everything that companies and individuals do, and many things that we cannot".

This combination of technologies, the LEF believes, will mark a major new phase of innovation which it has dubbed 'The Matrix' in a nod to the cyberpunk films released across the late 90s and early 2000s.

In essence, the Leading Edge Forum suggests "an ever more capable digital ecosystem" is increasingly underlying business infrastructure, helping organisations to radically transform not only their business, but society in a way which will only get stronger over time as consumer expectations rise...
Click to expand...

Read more: Cloud plus artificial intelligence is creating The Matrix (and that's a good thing) | ZDNet

Windows 10: Bringing intelligence to the edge with Google Cloud IoT Edge

Bringing intelligence to the edge with Google Cloud IoT Edge

Bringing intelligence to the edge with Google Cloud IoT Edge

Bringing intelligence to the edge with Google Cloud IoT Edge

Bringing intelligence to the edge with Google Cloud IoT Edge - Similar Threads - Bringing intelligence edge

CES 2020: Intel Intelligent Tech Spanning Cloud, Network, Edge and PC

Intelligent edge gets security and manageability of Windows 10 for IoT

Microsoft bringing cloud powered voices to Microsoft Edge Insiders

Microsoft Unboxed: The Intelligent Cloud and Intelligent Edge Ep. 13

Evolution of Windows IoT: The foundation for your intelligent edge

Latest Windows IoT innovations for intelligent edge devices

Do more at the intelligent edge with Windows 10 IoT

Windows IoT intelligent edge with Windows 10 April 2018 Update

Windows IoT intelligent edge with Windows 10 April 2018 Update