Data Drives Design – Conversations in IoT Architectural Design

 

In 2015, there were 15.41 billion connected Internet of Things (IoT) devices around the world. By 2020, just two years from now, that number will nearly double to 30.73 billion.1 Manufacturing, healthcare, and insurance are the top three industries that have the most to gain from IoT.2

Dealing with the data from these devices has become one of IT’s and IoT’s biggest challenges. In manufacturing, for example, by 2020, industrial IoT alone will generate a petabyte of data per day,3 including a new highly valuable data type—video.

 

Video—Eye of IoT
Video is widely considered the eye of IoT. It is a game changer. Vision technology is helping companies use video and images to better understand their business in transportation, public services, retail, industrial manufacturing, healthcare, and more.

Tens of millions of connected video devices across many sectors will generate massive amounts of data in both size and volume—a single raw 4k UHD frame is 8 MB. With so many cameras generating streams of 30 frames per second (fps) or more, it adds up quickly, even with today’s high-efficiency codecs. Cisco predicts that by 2021, video will be 82 percent of all IP traffic.4  It is becoming abundantly clear that data is expanding at an incredible rate.

Learn more about computer vision.

Dealing with Data
The IoT application and solution architects are on the front lines to deal with the challenges from increasing data variety, volume, and velocity. Their challenges include latency that impacts the availability of data, security of information, and cost to manage and move the data. Let’s look at each of those more closely.

Latency—When data has to be analyzed and responded to in real-time, any delay is a formula for failure. Even with data traveling on the fastest networks, massive amounts converging on a local network and then a backbone can still take many seconds to reach a data center thousands of miles away, be analyzed, and the response returned to the recipient. And, even with traffic prioritization, volume and distance to destination can delay critical information. When time is of the essence—when the analytical response to that data involves human safety or precision machinery—a delay could be the difference between success and disaster, and as a result, many choose to keep the time-critical analytics close to the source.

Security and Privacy—Some industries have strict regulatory requirements (e.g. HIPPA), and companies that generate highly sensitive Intellectual Property (IP) or operational data must secure and protect it. It creates a violation of personal information protection or an unacceptable business risk if the data is exposed or stolen. Cloud-based IoT solutions do not make sense for these companies; they need an in-house solution—with designed-in security and protection—where their business and operations execute, even while handling the massive amounts of data that might be generated locally.

Cost—Network technology is advancing. We are on the verge of wide 5G mobile deployments, increasing mobile network speeds. But, when every byte has a value tied to it, the cost of transporting large amounts of video across metered networks makes it prohibitive.

With issues like these, analysts predict that 45 percent of generated data will be processed, stored, and acted on at the edge by the end of next year.5

Designing for Data Processing at the Edge

The availability of advanced processing capabilities designed for the edge enables data to be handled locally instead of in the cloud, or before being sent to the cloud. These latest-generation technologies are provided for high-performance inferencing, analytics, general purpose compute, and Artificial Intelligence/Deep Learning (AI/DL) at the edge for the unique use cases presented to IoT solution and application architects.

Designing an edge compute solution for emerging applications is driven in large part by the type of data, the size of the data, the volume of data to be processed, and how fast it needs to be analyzed. When it comes to combining inferencing, general compute, storing and securing of data, and analytics at the edge, the Intel® Xeon® Scalable Processors and Intel® Xeon® Processor D family are a must have foundation to build on. Intel Xeon processors offer two to twenty cores to match the performance needs of edge systems, with extensibility to eight processors on a platform. Intel Xeon D processors offer scalability at a compact form factor and lower power.

These CPUs perform well for AI/DL applications and are optimized to handle new emerging use cases involving video analytics, pattern recognition, predicting outputs, and operational efficiencies. Intel Xeon Processors are designed for massive volumes of data, with multiple Ethernet connectivity, large memory capacity, and abundant I/O. Built-in security technologies enable developers to easily design in security from the architectural stage down to implementation, using advanced encryption and compression acceleration, platform and boot integrity, and a host of other security capabilities built into the processor silicon.

Intel offers specific Xeon products to operate in extreme environment conditions, and Intel supports IoT with extended product availability. Intel Xeon D Processors offer wide temperature ranges with Intel Xeon processor-class performance at relatively smaller form factor and power envelope, making them suitable for deployment at places such as oil and gas fields, mines, wind turbines, and factory floors. Plenty of options are available to find the right set of Intel Xeon processors to meet the performance, power, size, and reliability of edge systems.

And there are other compute options where specific types of processing are needed.

Intel® Vision products, including Intel Xeon processors, accelerate the capabilities of IoT vision systems and deep learning inference from the camera to the cloud through leading heterogeneous hardware and software combinations. We also provide the OpenVINO™ toolkit to fast-track the development of computer vision and deep learning inference into vision applications. Intel offers the broadest range of vision products and software tools to help OEMs, ODMs, ISV’s and system integrators scale vision technology across infrastructure, matching specific needs with the right performance, cost, and power efficiency at every point in an artificial intelligence (AI) architecture.

Additionally, our Intel® Core™ processor and Intel® Atom™ processor families have their place in edge computing as well.
Find out more about powering high-performance edge computing with Intel Xeon Scalable processors.

Accelerating and Optimizing IoT Application Development
Applying a choice (or choices) of technologies to enable insight and control operations from massive amounts of data is the job of the IoT architect and designer—a job that has components of complexity, competitive urgency, and, of course, lots of data. That’s why Intel has invested deeply in creating resources to accelerate IoT development and simplify the IoT developer journey.

In order to create solutions to handle data at multiple different stages and levels, architects must carefully consider the software investment and ecosystem. Intel provides a large portfolio of highly optimized libraries for Intel products and supports a strong software ecosystem for Intel Xeon processors. These libraries significantly boost the performance of data-intensive applications and make it increasingly easier to port code from generation to generation and improve reusability. Additionally, Intel also invests in optimized versions of open source artificial intelligence frameworks, which can improve the deep learning performance of the applications.

For example, Intel recently announced its OpenVINO™ toolkit for accelerating development of computer vision solutions. The OpenVINO toolkit was built to be the developers’ toolset of choice for visual understanding, from algorithm development to platform optimization. It assists developers in creating and deploying optimized computer vision solutions using industry standard APIs, frameworks, and libraries. OpenVINO allows developers to take networks created in common frameworks, like Caffe, Tensorflow, and MXNet, and optimize those on heterogeneous hardware engines from Intel. OpenVINO is just one such toolset from Intel.

These optimized libraries, various SDKs, and frameworks make it seamless for a designer to extract the best out of Intel products with little to no effort. These can all be found online. They are also bundled with applicable developer kits available from Intel IoT ecosystem partners. The kits further accelerate time to market by providing hardware, software, tools, code samples, and more to help developers get started quickly.
Learn more about accelerating vision computing with the OpenVINO toolkit.

Our Vision is to Help You Deliver Your Vision
The need to process data at the edge drives IoT design. The choice of technologies to be used in that design falls to the IoT architect, who faces significant challenges to get a solution running quickly. At Intel, we are trying hard to simplify the IoT developer’s journey and accelerate their time to solution with a range of proven Intel Xeon processors, and Intel technologies and resources that address key challenges. Visit the IoT Developer Zone to find out how these resources can help you on your journey at software.intel.com/iot.

Next Time
Information security and data protection are critical to many IoT environments. Markets where personal information is scrutinized and regulated by government agencies, such as healthcare and insurance, are a couple examples. Designing in security becomes top of mind for architects building solutions for such markets. I’ll take a look at designing in security and protection in IoT development in the next article.

_____________________________________________________________________________________________

1https://www.statista.com/statistics/471264/iot-number-of-connected-devices-worldwide/
2https://planetechusa.com/blog/how-much-data-will-the-internet-of-things-iot-generate-by-2020/
3Amalgamation of analyst data and Intel analyses.
4https://www.cisco.com/c/en/us/solutions/service-provider/visual-networking-index-vni/index.html
5http://www.cisco.com/c/en/us/solutions/collateral/service-provider/global-cloud-index-gci/Cloud_Index_White_Paper.html

 

 

 

 

 

The post Data Drives Design – Conversations in IoT Architectural Design appeared first on IoT@Intel.

Go to Source
Author: Jonathan Luse