Posted on Leave a comment

Matter: a Unifying Standard for Home Devices or Hype?

In this short article I want to discuss the release of the recent standard, Matter, formally CHIP (Project Connected Home over IP). Will we have a consumer device communication standard that’s ideal for the smart home or are we looking at yet another standard that will further complicate IoT for the our smart appliances?

Matter was parented by the Connectivity Standards Alliance and release to the world this month. Version 1 is available now for review by manufacturers, developers, and anyone curious about this new means of device communications.

The goal of this standard is to make interoperability among home devices easier. And because the standard has backing from Samsung, Google, Apple, and a large number of other organizations with interest in the home device market, there appears to be a fair chance the standard will stick.

The promise seems to be less hassle for the user. When you purchase a product that adheres to the Matter standard, you should be able to easily connect and integrate with other devices in your home using that standard.

But what about security? Even at this moment, I can connect to my neighbor’s TV from my iPad if I wanted to. How do we make sure that these devices are safe, even for those who aren’t the most technically skilled?

According to their security white paper, Matter follows five security tenets:

  • Comprehensive – they use a layered approach
  • Strong – they use well-tested, strong cryptography
  • Easy – security should improve ease of use, or decrease it
  • Resilient – protect, detect, recover
  • Agile – able to respond quickly to threats

How easily will this be adopted by the developers? I did take a look at the source code and libraries. It’s written in C++, so it should be fast. And there appear to be libraries for most of your common development boards, chipsets, and MCUs. I think that’s good sign. You can see the repo here:

So is it a viable standard or is it hype?

Matter was a long time in the making. And it’s creation required manufacturing rivals like Google, Apple, and Samsung to sit across from each other at a table and agree on one direction to take device communication. The standard was just released this month and the official launch is on November 3rd. There are already a large group of early adopters prepared to launch products. Some of your appliances under the Christmas Tree this year might be Matter compatible.

I think it’s safe to say that Matter isn’t just hype. It looks to be a great way for devices to communicate easily on a home network using common IP methods and options like WiFi and a new protocol called Thread. Maybe this time next year we’ll see more IoT innovation in our homes because of better device interoperability.

Posted on Leave a comment

The Smart Factory for Brewers isn’t Just for the Big Brewers; is Your Independent Brewery Ready for IoT, AI, and the Cloud?

Wouldn’t it be great if every beer bottle that left your brewery met with your exacting quality standards, if overflowing and excessive foaming were yesterday’s problem, and not a persistent, wasteful expense?

What if you could be consistently proactive in your quality control process, and not reactive to cases of returned beer and disappointed customers?

Independent breweries like Sugar Creek Brewing faced just such a problem, and according to this Forbes article, the problem cost the brewery $30,000 a month.

Independent, hand-crafted breweries are discovering what manufacturers have understood for decades. You can measure product quality with IoT. But many breweries, like Sugar Creek Brewing, are using AI to predict quality issues before they happen allowing brewers to proactively manage the quality of their beer.

The Smart Factory for the Independent Brewery

The smart factory for breweries is here. Connecting your brewery with IoT devices capable of streaming real-time data to the cloud, analyzing that data with AI, and creating a responsive feedback loop that your employees can use to consistently improve the brewing process is no longer a tool meant only for the larger brewers with immense IT teams and budgets.

To help pinpoint the specific causes of overflow and excessive foaming during the brewing and bottling processes, you can connect your equipment with embedded flow meters and sensors that allow you to collect a high volume of accurate data on pressure, temperature, pH balance, carbonation, fill time and more.

By collecting all this data and applying the correct analytics, you can discover insights about your operations, improve efficiency, stop equipment bottlenecks, and help your employees accomplish their daily tasks.

Working around high-pressure tanks presents big risks to employees working on the production line. With the right pressure sensors on every kettle, still, brewing pump, and with object detection in place, the factory floor can become a much safer place to work, as production managers can track performance issues that could lead to serious injuries.

The fermentation process is the heart of the brewery factory. What if you could get constant feedback on this process without opening that tank?

Breweries See a Return on their Investment with AI and IoT

Not only does the Smart Factory for Breweries improve efficiency, beer quality, and employee safety, but it also helps improve your brewery’s financials.

  • Save on returns from poor quality products
  • Reduce waste of materials for bad batches
  • Fully use capital equipment
  • Protect the health and safety of employees and customers
  • Reduce energy use
  • Monitor and track batches effectively for compliance and regulations
  • Save on parts and repairs using AI predictive maintenance
  • Control inventory with RFID tracking

The cloud has allowed the cost of analytics systems to drop significantly, and many IoT platforms can right-size their solutions to fit with your consumption, giving you the option to ease into your IoT and AI journey affordably.

Connecting KPIs as a Measure of Success

As a brewer, you’ll want goals and specific metrics tied to your Smart Factory for Breweries. Some of these include the following depending on your solution approach:

  • Equipment downtime for repairs
  • Predictive cleaning schedule vs set schedule
  • Returns from retailers because of quality
  • Bbl brewed per hour
  • Bbl packaged per hour
  • Bbl lost per hour
  • Bbl to energy costs

Your Business Processes will Need to Adapt

There are daily processes undertaken in the brewery that add to waste and risk contamination. The typical small brewery will draw liquid from the tanks daily to check for quality, consistency, and the state of the fermentation process. This is the process of monitoring specific gravity. It’s not a great process when managed manually, because only checking once or twice a day isn’t likely to catch a problem quickly enough, and with each test the product is exposed to possible contamination.

To reduce the risk of contamination and increase regular monitoring, it makes sense to add a sensor to the tank to collect data. The data collected from the tank can then inform operations.

But how is this continuous monitoring done on large tanks that are usually made of copper or industrial steel? This is where it helps to understand the problem and find the right IoT device for the job. In this case, low energy Bluetooth devices floated in the liquid can communicate with gateways positioned nearby. This allows IoT to completely replace a manual process, as well as do a better job of monitoring for regular consistency.

This is why it’s important to work directly with a partner who can help match the right product with the situation. A great partner will learn your business processes and won’t be afraid to point out where your business process will need to adapt to fit with the innovation the technology brings.

A Use Case: Automate the Manual Method of Measuring Specific Gravity

Brewers are well aware of how this process works, but for this use case I’ll summarize it:

Specific gravity will indicate the stage of fermentation. Brewers use this measurement to determine the state of fermentation—is it on track, done, or perhaps stuck. Yeast can stop consuming sugar too early, and when this happens the brewer needs to take steps to save the batch. This is one of the reasons continuous monitoring is required for the modern brewery. The sooner you’re aware of a stalled batch, the sooner you can undo the damage.

This is typically measured using the manual method described above. The actual measurement is looking at the liquid’s density in comparison to water. As beer ferments and coverts sugars to alcohol and gas, the specific gravity falls and the liquid gets less dense. Eventually, there are few sugars left and the fermentation process slowly stops.

It’s clear to see why putting a machine in charge of monitoring this process consistently helps improve this task.

But what does this look like, technically? Are there tools and systems in place today to make this easy to install and monitor without risking batches of beer or installing expensive equipment?

Tilt Pro, Bluetooth, and IoT Central

If we focus on one particular use case, like measuring specific gravity, there are a number of ways to accomplish this, but the following architecture is one that I recommend. This architecture is built for a small brewery with just a few fermentation tanks. It uses off-the-shelf devices and requires minimum programming to get the solution up-and-running. But it also has room to grow into a robust platform for managing more than just fermentation monitoring.


The assumption is that you’re using industry standard fermentation tanks. These are, without a doubt, a challenge for electronics equipment. Most are made of steel or copper, which means that they basically act like a Faraday Shield capable of blocking or dampening signals.

Some IoT devices will not work in this situation. So either you need a wired solution or something clever like the Tilt Hydrometer. When I first discovered this device I thought that perhaps it was a toy for homebrewers. Surely, nothing as low in price as this device could have professional applications, right? Well, after reviewing the device and seeing it’s capabilities on paper, I’m willing to include it in this architecture.

Especially, backed up by a custom device to work with the iBeacon signal generated from the Tilt. For this architecture, I’m recommending the Tilt Pro. The standard Tilt device might be adequate, but I think it’s worth the extra money for the added battery life and sensor capabilities.

The Tilt device goes inside the tank, but it’s enclosed in a protective shell. Cleaning and care instructions are available on their website. Here’s the marketing breakdown on the device:

At 3x the volume and weight of our original Tilt hydrometer, the Tilt Pro’s larger size allows us to more than double the battery life with preinstalled Energizer® AA lithium batteries that will keep it powered for 3 to 5 years depending on use. So much time you may forget your Tilt actually runs on a battery! The extra size and weight comes with an extra bonus: improved specific gravity stability at high krausen so you will see a steadier read-out on your iPhone, Android, or Raspberry Pi. In addition, we have boosted range with a high-gain antenna that in testing increased range by 20% vs. our original Tilt. Now you can see your Tilt through thicker heads of foam and heavier stainless steel walls. To top it off we’ve included the extra decimal of precision available from the sensors and to the read-out so there are now decimal degrees Fahrenheit as well as higher resolution Celsius. Specific gravity now reads out to the 10,000th place (for example 1.0000). You can now see fermentation activity dropping less than a brewer’s point per day. In all we’ve made several adjustments we believe the craft beer professional (and serious home brewer) is sure to appreciate.

The Tilt’s cloud backend is basically writing data to Google Sheets. We definitely don’t want to write our data to Google Sheets. No offense to Google Sheets. It’s a great app for many purposes, but we want something a bit more robust. I also do not want a mobile app. I want a device dedicated to capturing the Bluetooth signal, converting the raw message from that signal to MQTT, and delivering that to a server on the Brewery’s internal network.


The basic flow of data from tank to IoT gateway looks like the following:

The Tilt is a one-way leaf device and it’s tightly coupled to a nearby Raspberry Pi Zero W. By nearby, I mean as close to the tank as possible, other than inside of it.

The Pi gives us a lot of development options. We could, if we wanted to, connect the Pi directly to Azure IoT Central. This would make it a gateway device. It would still need a WiFi router or hub to connect to, but it could manage two way communication with IoT Central.

For this architecture, though, I want to couple a Pi with each Tilt. Considering that the cost of each device is minimal and the power you get when you add a more robust gateway, like the Ectron Edge Computer ECT-ECI, this allows us to remain technically small and simple, but with the option of applying more sophisticated Edge Patterns.

For instance, there might come a future date when I want to I want to deploy machine learning modules to the Pi. These modules could be specific to each tank’s beer, allowing brewers the ability to monitor for different types of beer.


The following is our more robust design.

I want to continue with the idea that this is just a proof-of-concept set with one use case. However, I’ve expanded out to manage three different tanks. Each tank as been coupled with its own Tilt device, Raspberry Pi Zero W, and all three of these connect to the Ectron Edge Computer.

Where we start to flesh out the solution, is when we collect the data in the cloud. Here we’re using Azure’s IoT Central, but we could just as easily use any other cloud IoT platform. I like IoT Central because it’s quick to get an app up-and-running, it makes device management simple, and includes all the analytics you need to prove out an IoT POC.

It’s also scalable, so building out to more devices and more use cases is easy. IoT Central is meant for smaller to mid-sized IoT projects, but it can still support multiple organizations in production scenarios.

When you start to work with more than one million devices, though, IoT Hub, AWS IoT SiteWise, or Google’s IoT Core are better choices. Though I designed this with Azure in mind, the Gateway is flexible enough to work with any cloud backend IoT service.

A couple of future use cases we could explore once this platform is built:

  • Use Machine Learning to predict fermentation stages for specific beers
  • Use time series analysis to detect anomalies in the brewing process
  • Collect data specific to certain recipes, build guidelines and intelligent monitoring around these recipes, and alert Brew Masters to tanks that drift outside the confines of the established guidelines

Who do I need to put this solution into place?

The team to build this out could be relatively small. One person with the right skills could build this entire solution, but what skills will they need?

  1. The Tilt devices are relatively complete. As an off-the-shelf solution they provide a lot of flexibility. To work with this device, you’ll need to understand how to collect Bluetooth Beacon data. Lucky for us, Tilt includes a link to work with this data from their website’s FAQ.
  2. Creating the coupled Pi Zero will pose a slightly bigger challenge. This isn’t an out-of-the-box solution, but it isn’t undiscovered country either. Basically, we want to run Containerd and the IoT Edge Modules on the device. This will allow us to deploy to the Pi as though it were an Edge Device. We could also use the IoT Central SDKs to create a basic device and send data. We have a few choices here but ideally, you want to capture the BLE message, format it to something that best fits the use case, and then wrap that in an MQTT message to send to IoT Central.
  3. The Edge Gateway is probably one of the easier pieces to implement. This article covers the process, so I won’t dive into it here:
  4. Setting up the Edge Gateway and devices in IoT Central, is also trivial, but that might be a different person completing the set up than the device developer.

Basically, if you have someone with experience developing IoT Edge modules, lite Python programming skills, and IoT Central administration basics, you could have a solution up-and-running quickly.

Is this Secure?

If you keep the signals within the brewery on their own dedicated network and authenticate the devices through IoT Central, it should be secure. The real trick here is to make sure you provide a separate network on your brewery floor from the rest of the company’s network. For instance, many breweries are also open to the public for dining and tours. You don’t want the public to even be able to see the brewery floor network, much less access it from their devices.

In this scenario, the endpoints for IoT Central are the only exposed URLs. You can protect these with device authentication. Logging into IoT Central as an administrator would be protected by Azure Active Directory using MFA.

What about my data? Is it backed up?

IoT Central only stores about 30 days worth of data, but there are means of integrating storage solutions with your IoT Central App. This isn’t reflected in this architecture, but at a minimum I would recommend adding an Azure Storage Account to retain messages. You’ll likely want this data for future data science and trend analysis.

What if I have more than one brewery?

This solution isn’t designed for extreme robustness or resilience. I definitely put this solution in the category of proof-of-concept or minimal viable product. If you set this up, and you like your initial tests, and you feel like this is something that could expand to multiple physical locations, IoT Central can definitely handle this up to 1 million devices. If your device requirements look like they will spread beyond that number, it’s time to consider Azure’s IoT Hub solution with a more complete Azure Analytics backend. Synapse or Databricks with Azure Time Series Insights make great additions to this type of architecture.

How do I manage this environment

As long as this is kept small, it’s probably ideal for a single developer or administrator. IoT Central has a few built in roles that the administrator or App owner can assign to users so they have access to dashboards. At a minimal, I would consider these roles in IoT Central:

  • Application Administrator can manage and control every part of the application – give this role to someone in your IT operations department
  • App builder has many of the same abilities as the Admin, with the exception that they can’t make administration changes or connect to data exports
  • The Operator role is ideal for someone who needs to monitor device health and status. This is for anyone working the brewery floor

Those are basic roles. If you begin to build your solution out to multiple locations, these can be defined as Organizations. If I own a brewery in three different cities in my state, I might have my Fort Worth brewery, my Dallas brewery, and my Austin brewery. I would separate those by Organization and assign the above roles to users in those areas.

What can I do with this platform, once it’s up-and-running?

IoT Central comes with many tools needed to run operational IoT.

  • Robust Dashboards that can be customized for many different views
  • Device life-cycle management and Gateway management
  • Rules triggered based on telemetry with built in messaging to email, webhook, Azure Monitor Action Groups, Microsoft Power Automate, and Microsoft Azure Logic Apps
  • Time-series Analytics allows you to create and save queries
  • Run jobs on device groups that can send commands to devices or change device properties
  • Build and store device templates
  • Export to multiple data sources
  • Complete administration of the app, the users, and pricing

In addition to the IoT Central benefits, you can build upon the IoT Edge devices by integrating device specific logic or machine learning models.

If I have an IT team, will they need a lot of training?

Perhaps, if they aren’t familiar with IoT. However, Azure does make some of this fairly easy. It helps to work with a partner who understands how to make cloud solutions operational. Knowing and understanding the burdens and responsibilities of a lights-on operations team will help your partner understand what things the team needs to monitor for and integrate into your team’s existing playbooks and operations procedures.

I’m interested to see how IoT can help my brewery

If you aren’t already using IoT in your brewery, it’s important to understand that there is a learning curve. As I’ve outlined here, it takes some time to understand how the technology can help you and how you might need to adapt to the technology. If you have the right partner, this can be a smooth transition. There are definitely some key stages I think a partner should walk you through before you make a large financial commitment.

  1. Be careful with any solution that appears to be a one-size fits all. Your brewery is unique. Your product is unique. You didn’t become an independent, craft brewer because you wanted to mimic a certain company with the initials of AB. So AB’s amazing, multi-million dollar IT solution probably isn’t right for you.
  2. This isn’t a quick, one-and-done project. IoT is a journey best taken in measured steps. The right partner is going to understand that process and they will help guide you along the path.
  3. The right partner takes a wholistic view of you, your brewery, and cares about your bigger picture goals. Selling gadgets is great, if all you do is sell gadgets, but a solutions partner wants to make sure you have the right gadget for your needs.

Solution Visioning

Expect a couple of workshops from your solution partner. Believe it or not, these aren’t just a way to make more money off of you. These are a necessary part of the process. A partner needs to learn about you, your business, your aspirations and your challenges. These envisioning workshops are a way to achieve that.

Architectural Understanding

A good partner will want to understand your network topology, but also your enterprise architecture. Not just the technical systems, but your policies, procedures, your team structure, and even your company culture.

POCs and Pilots

Smaller, measured steps into a bigger picture solution is a great way to learn, without breaking the bank. The days of huge, multi-year projects only to deliver a technical nightmare that doesn’t meet your needs is gone. Be ready to work with a partner willing to take small steps toward bigger goals.

  • Limit your use case to one single point of value
  • Limit your scope to one particular area of the brewery
  • Time-box your efforts. Don’t make the mistake of trying to enforce an artificial deadline, but don’t get mired in complexity.
  • A POC won’t be production ready, but it will be testable with real-world scenarios
  • Take this opportunity to learn and try to avoid assumptions
  • It might require multiple POCs to arrive at a worthwhile pilot
  • It will require your time, the time of your staff, and your feedback—you can’t hand off your standard operating procedures and expect a bespoke solution to your particular needs

How do we make this production ready?

When you’re prepared to take this solution to production, there are a few factors to consider.

  1. How do we reach zero-trust security with this platform? Are our users authenticating using MFA. Does each user have the least privileges possible? Are my devices hardened against tampering? Are my Edge devices loaded with security modules?
  2. Do I have system oversight? Is there the appropriate level of logging and log monitoring in place? Are there alert groups established in Azure. Are these alert groups receiving alerts from IoT Central, devices, and any other backend analytics systems?
  3. Is data backed up securely? Is access to this data limited to integrated systems? Is access to the data monitored?

There are other considerations like building out staging layers for developers and testers. A more complete security monitoring tool like Microsoft Defender for Cloud should be a consideration. Hiring penetration testers to test your security is also a good idea.

Teaching your team how the system works

Hopefully your team has been involved from the beginning. A good IoT integration partner will talk to the brewery floor crew during development and system installation, get their feedback for alerts and dashboards, and familiarize everyone with the systems as it’s built.

Good formal training for the brewer floor will be something a partner can provide. Delivering this training in documentation, video, and one-on-one sessions is the typical method for handing off a production system. As your system grows and matures, you’ll eventually want staff trainers who have made your technical solutions part of your floor’s standard operating procedures.

What if I need continued help after the solution is built?

Let your partner supplement your time with ongoing support and monitoring. Many IoT developers and integrators either have a managed service team or they outsource that job to a trusted partner. If you don’t have the IT staff to manage and monitor your solution, your IoT partner should be able to provide one for you at an affordable rate.

Who do I include in partner meetings?

Independent brewers tend to keep the company lean. Titles like CEO, CTO, and CFO might not exist. That’s not a problem. The people who need to be at the table are decision makers, financiers, brewery operations experts, and trusted advisers.

Are you available to help us?

Yes, as a certified Azure IoT specialist and AI Engineer with twenty years of IT experience, I’m in the ideal place to help with this exact type of solution. I’m a strong advocate of cloud transformation. I’ve helped large and small organizations transform their operations using Azure and Big Data analytics platforms. I’d love the opportunity to work with a brewery interested in exploring how IoT could improve their operations and save them thousands of dollars a month.

What are the next steps?

Are you happy with your current brewery floor operations? Now that you know there are better ways to brew beer, can you continue to operate the same way moving forward? Inertia is difficult to break, but one thing that helps is a clear decision. Is a Smart Factory for Breweries something you’re ready to take on? Or can you continue on your present path?

When it comes to these type of decisions, it’s usually best to start small. This is one of the reasons I’m an advocate of the POC. With a small equipment investment, an Azure subscription that only charges based on consumption, and a hands-on consultant who can take you through every step of the process, it’s easier now than ever before to test your ideas without breaking the bank.

The cloud, IoT, and AI are tools that brewers use to improve operations, innovate, and save money. If you’re interested in seeing if this is the right path for your brewery, I’m here to help.

Posted on Leave a comment

I Read and Summarized the 3rd Edition of IoT Signals So You Don’t Have to

A report built based on survey data taken by the company named, ‘hypothesis’. This is a combined effort between Microsoft and Hypothesis to capture the most current state of IoT from the view of business leaders in certain sectors; manufacturing, energy, mobility, and smart places.

The survey was multi-national and the report includes data captured from in-depth interviews.

Things to know about IoT in 2021

The following are high-level conclusions drawn from the interviews and survey data:

  • IoT continues to drive organizations toward a more productive future
  • COVID-19 has accelerated IoT strategies and fueled business growth
  • AI, Edge Computing, and Digital Twins are essential to advance IoT strategies
  • Although IoT projects are maturing, technological complexity persists
  • Organizations are keeping a close eye on data security

Who they talked to

  • Business decision makers, developers, and IT decision makers who work at enterprise-size companies with greater than 1k employees
    • 71% were familiar with IoT
    • 95% of those familiar, have influence and decision making power on IoT strategies
      • 10% of those familiar were not in adoption of IoT
      • 90% of those familiar were in adoption of IoT

Overall Research Learnings

Big Picture

This year, IoT continues to be widely adopted. 90% of organizations surveyed are IoT adopters. IoT projects can be categorized into four stages:

  • Learn
  • Trial / Proof of Concept
  • Purchase
  • Use

Of the 90%, at least 82% have a project that reached the “use” stage.

The state of most projects overall:

  • 29% in Learn
  • 25% in Trial / POC
  • 22% in Purchase
  • 25% in Use

IoT adoption and value globally (Australia, Italy, and the US lead as primary adopters)

  • 90% of the surveyed leaders in countries fitting criteria are adopters
  • 25% have projects in use
  • Average time to reach “use” is 12 months
  • 66% plan to use IoT more in the next 2 years

IoT Adoption and Value by Industry

  • Manufacturing
    • 91% of the surveyed leaders in countries fitting criteria are adopters
    • 26% have projects in use
    • Average time to reach “use” is 13 months
    • 68% plan to use IoT more in the next 2 years
  • Energy
    • 85% of the surveyed leaders in countries fitting criteria are adopters
    • 22% have projects in use
    • Average time to reach “use” is 15 months
    • 61% plan to use IoT more in the next 2 years
  • Mobility
    • 91% of the surveyed leaders in countries fitting criteria are adopters
    • 23% have projects in use
    • Average time to reach “use” is 14 months
    • 61% plan to use IoT more in the next 2 years
  • Smart Places
    • 94% of the surveyed leaders in countries fitting criteria are adopters
    • 24% have projects in use
    • Average time to reach “use” is 13 months
    • 69% plan to use IoT more in the next 2 years

Why Adopt IoT

Overall Top 5 reasons:

  • Quality Assurance : 43%
  • Cloud Security: 42%
  • Device and Asset Security: 40%
  • Operations Optimization: 40%
  • Employee Productivity: 35%

The report includes evidence that those companies who employ IoT to improve products and service see a higher increase in overall ROI.

Manufacturing Top 5:

  • Quality and compliance
  • Industrial automation
  • Production flow monitoring
  • Production planning and scheduling
  • Supply chain and logistics

Energy (Power and Utilities) Top 5:

  • Smart grid automation
  • Grid asset maintenance
  • Remote infrastructure maintenance
  • Smart metering
  • Workplace safety

Energy (Oil and Gas)

  • Workplace safety
  • Employee safety
  • Remote infrastructure maintenance
  • Emissions monitoring and reduction
  • Asset and predictive maintenance


  • Inventory tracking and warehousing
  • Manufacturing operation efficiency
  • Surveillance and safety
  • Remote commands
  • Fleet management

Smart places

  • Productivity enablement and workplace analysis
  • Building safety
  • Predictive maintenance
  • Regulations and compliance management
  • Space management and optimization

Benefits of IoT

Top 5 benefits organizations are reaping from IoT

  • Increases in efficiency of operations
  • Improved safety conditions
  • Allows employees to be more productive
  • Allows for better optimization of tools and equipment
  • Reduces chance for human error

Common measures of success in IoT

  • Quality
  • Security
  • Production Efficiency
  • Reliability
  • Cost efficiency

Less common measures of success

  • More informed decision making
  • Direct impact on increased revenue
  • Sustainability
  • % of project deployed using IoT

Challenges of IoT

Top 5

  • Still implementing our current solution
  • Security risk isn’t worth it
  • Want to work out existing and future challenges before adding or using IoT more
  • Too complex to implement because of technology demands
  • Too complex to implement because of business transformation needed

Top 5 reasons POCs fail

  • High cost of scaling
  • Lack of necessary technology
  • Pilots demonstrate unclear business value or ROI
  • Too many platforms to test
  • Pilot takes too long to deploy

Top 5 security concerns

  • Ensuring data privacy
  • Ensuring network-level security
  • Security endpoints for each IoT device
  • Tracking and managing each IoT device
  • Making sure all existing software is updated

The report includes a section on best practices, and notes that despite security being a big concern, very few are implementing these best practices:

Top 5 best practices

  • Assume breaches at every level of IoT project
  • Analyze dataflows for anomalies and breaches
  • Define trust boundaries between components
  • Implement least privileged access
  • Monitoring 3rd party dependencies for common vulnerabilities

IoT Implementation Strategy

Most of the companies surveyed prefer to work with outsourced resources to implement their IoT strategy. They do prefer bespoke solutions.

Those who outsource see these positive benefits:

  • Increases efficiency of operations
  • Improves safety conditions
  • Reduces changes for human error

Those who do not outsource tend to hit these challenges:

  • Too complex to implement because of business transformation needed
  • Too long to implement
  • No buy-in from senior leadership


Companies with more near-term zero carbon footprint goals are more motivated to implement IoT to help than those who have a longer range target.

Impact of COVID-19

When asked if C-19 was an influence in investing:

  • 44% more investment
  • 41% stay the same
  • 7% less
  • 4% too early to tell

Emerging Technologies

Those who are adopting IoT are more likely to adopt other innovative technology associated with IoT:

  • Digital Twins
  • Edge Computing
  • AI at the Edge

This is collectively known as AI Edge

AI Implementation

84% Have a strategy:

  • 31% are implementing
  • 26% developed, but not implemented
  • 26% developing

16% do not have a strategy

  • 11% want to develop
  • 5% have no plans

79% of respondents claim that AI is a core or secondary component of their overall IoT strategy

Top 5 reasons for AI in IoT Adoption:

  • Predictive maintenance
  • Prescriptive maintenance
  • User experience
  • Visual image recognition and interpretation
  • Natural language recognition and processing

Top 5 Barriers to using AI within IoT

  • Too complex to scale
  • Lack of infrastructure
  • Lack of technical knowledge
  • Implementing AI would be too complex
  • Lack of trained personnel

AI Adoption and Value by Industry


  • 84% – have an AI strategy
  • 31% – Implementing
  • 26% – developed
  • 26% – developing
  • 79% – use AI in IoT solution


  • 84% – have an AI strategy
  • 31% – Implementing
  • 23% – developed
  • 30% – developing
  • 83% – use AI in IoT solution


  • 90% – have an AI strategy
  • 26% – Implementing
  • 28% – developed
  • 36% – developing
  • 89% – use AI in IoT solution


  • 81% – have an AI strategy
  • 36% – Implementing
  • 25% – developed
  • 20% – developing
  • 85% – use AI in IoT solution

Smart Places

  • 88% – have an AI strategy
  • 39% – Implementing
  • 28% – developed
  • 21% – developing
  • 75% – use AI in IoT solution

Edge Computing

Edge Computing Implementation Progress

79% have a strategy:

  • 29% implementing
  • 26% developed but not implemented
  • 24% developing

21% do not have a strategy:

  • 15% want to develop
  • 6% have not plans

81% Edge Computing as a core or secondary component:

  • 42% Core
  • 39% Secondary
  • 18% Considering, not yet adopted
  • 1% not considering

Top 5 Reasons to adopt Edge Computing

  • Cloud security
  • Device and asset security
  • Quality assurance
  • Securing the physical environment
  • Operations Optimization

Top 5 barriers to adoption

  • Lack of architectural guidance
  • Lack of trained personnel
  • Lack of infrastructure
  • Difficulty managing security
  • Lack of clarity on edge hardware choices

Edge Computing Adoption and Value by Industry


  • 79% – Have Edge Computing strategy
  • 29% – implementing
  • 26% – developed
  • 24% – developing
  • 81% – Use Edge Computing in IoT Solutions


  • 83% – Have Edge Computing strategy
  • 37% – implementing
  • 28% – developed
  • 18% – developing
  • 77% – Use Edge Computing in IoT Solutions


  • 85% – Have Edge Computing strategy
  • 38% – implementing
  • 25% – developed
  • 23% – developing
  • 85% – Use Edge Computing in IoT Solutions


  • 85% – Have Edge Computing strategy
  • 18% – implementing
  • 30% – developed
  • 37% – developing
  • 88% – Use Edge Computing in IoT Solutions

Smart Places:

  • 85% – Have Edge Computing strategy
  • 29% – implementing
  • 26% – developed
  • 30% – developing
  • 83% – Use Edge Computing in IoT Solutions

Digital Twins

77% have a strategy:

  • 24% implementing
  • 29% developed, but not implemented
  • 24% developing

23% do not have a strategy:

  • 14% want to develop
  • 9% have no plans

81% Use and Impact of DT on IoT Solutions

  • 41% feature as core component
  • 40% feature as secondary component
  • 18% considering, but not yet adopted
  • 1% not considering

Top 5 benefits of using DT within IoT:

  • Improve overall quality
  • Increase revenue
  • Reduce operations costs
  • Enhance warranty cost and services
  • Reduce time to market for a new product

Top 5 barriers:

  • Challenges managing the value of data collected
  • Complexity of systems needed to handle digital twins
  • Integration challenges
  • Lack of trained personnel
  • Challenges modeling the environment

Digital Twins Adoption and Value by Industry


  • 77% – have a DT strategy
  • 24% – implementing
  • 29% – developed
  • 24% – developing
  • 81% – use DT in IoT solution


  • 79% – have a DT strategy
  • 31% – implementing
  • 25% – developed
  • 23% – developing
  • 86% – use DT in IoT solution


  • 79% – have a DT strategy
  • 26% – implementing
  • 29% – developed
  • 24% – developing
  • 82% – use DT in IoT solution


  • 76% – have a DT strategy
  • 15% – implementing
  • 39% – developed
  • 23% – developing
  • 77% – use DT in IoT solution

Smart Places

  • 82% – have a DT strategy
  • 27% – implementing
  • 35% – developed
  • 22% – developing
  • 85% – use DT in IoT solution

By Industry

Smart Places

94% IoT Adopters

  • 27% – learn
  • 25% – POC
  • 25% – Purchase
  • 24% – Use

Top Benefits:

  • Increase the efficiency of operations
  • Improves safety conditions
  • Allows for better optimization of tools and equipment

Top 5 reasons for adoption:

  • Productivity enablement
  • Building safety
  • Predictive maintenance
  • Space management and optimization
  • Regulation and compliance management

Top 5 challenges

  • Still implementing current solution
  • Security risk isn’t worth it
  • Too complex to implement because of the need for business transformation
  • Want to work out exiting and future challenges before adding or using
  • Too complex to implement because of technology demands


91% IoT Adopters

  • 27% – Learn
  • 26% – POC
  • 21% – Purchase
  • 26% – Use

Top Benefits

  • Increases the efficiency of operations
  • Increases production capacity
  • Reduces chance for human error

Top 5 Reasons for Adoption:

  • Quality and compliance
  • Industrial automation
  • Production flow monitoring
  • Production planning and scheduling
  • Supply chain and logistics

Top 5 Challenges to using IoT more

  • Still implementing current solution
  • Too complex to implement because of technology demands
  • Security risk isn’t worth it
  • Want to work out challenges before adding or using IoT more
  • Don’t have human resources to implement or manage


91% IoT Adopters:

  • 30% – Learn
  • 26% – POC
  • 21% – Purchase
  • 23% – Use

Top benefits of IoT:

  • Increase efficiency of operations
  • Allows employees to be more productive
  • Improves safety conditions and increases production capacity

Top 5 Reasons for Adoption

  • Inventory tracking and warehousing
  • Manufacturing operations efficiency
  • Surveillance and safety
  • Remote commands
  • Fleet management

Top 5 challenges to using IoT More:

  • Want to work out challenges before adding or using IoT more
  • Too complex to implement because of technology demands
  • Still implementing our current solutions
  • Security risk isn’t worth it
  • Too complex to implement because of business transformation needed


80% IoT Adopters (Power and Utilities)

  • 28% – Learn
  • 26% – POC
  • 23% – Purchase
  • 23% – Use

Top Benefits

  • Increase the efficiency of operations
  • Increases production capacity
  • Allows employees to be more productive

Top 5 reasons for adoption:

  • Smart grid automation
  • Grid asset maintenance
  • Remote infrastructure maintenance
  • Smart metering
  • Workplace safety

Top Challenges:

  • Too complex because of technology demands
  • Security risk isn’t worth it
  • don’t have human resources to implement and manage

94% IoT Adopters (Oil & Gas)

  • 28% – Learn
  • 27% – POC
  • 24% – Purchase
  • 20% – Use

Top Benefits

  • Increase customer satisfaction
  • Improves business decision-making
  • Increases production capacity and the efficiency of operations

Top 5 reasons for adoption:

  • Workplace safety
  • Employee satisfaction
  • Remote infrastructure maintenance
  • Emissions monitoring and reduciton
  • Asset and predictive maintenance

Top challenges:

  • Lack of technical knowledge
  • Don’t know enough
  • Too complex to implement because of business transformation needed

Final Thoughts

Things worth noting:

  • IoT is not going away, in fact more money, time, and investment goes into it each year
  • Most organizations are looking to add AI, Edge Computing, and Digital Twins to their solutions
  • May organizations are outsourcing their IoT work and seeing more benefits because of this
  • Top challenges are around knowledge, skill, security, and implementation at scale

The original report

Posted on 1 Comment

Operationalize Machine Learning for Manufacturing

The “Smart” manufacturing revolution is here. It’s proved its effectiveness in Predictive Maintenance, Quality Control, Logistics and Inventory, Product Development, Cybersecurity, and paired with IoT it expands into Robotics, Control Systems, and Digital Twins.

Manufacturers who want to build a data science team and operationalize machine learning models for must build an MLOPs practice. And by must, I mean this is essential, not optional. I’ve seen what happens when a team is built of unskilled engineers and attempts to take shortcuts on the journey to put machine learning into production without MLOPs and Responsible AI.

Why do you need MLOPs?

First, I think it’s important to understand the benefits of machine learning to manufacturers. I’ve already touched on some of the areas where Machine Learning is helpful. But let’s talk about the value that MLOPs brings to your organization.

  1. It helps to reduce the risk of data science by making the work of scientists more transparent, trackable, and understandable. When coupled with a Responsible AI governance policy, MLOPs can help manufacturing leaders understand the risks of the models running in their environments.
  2. Generate greater, long-term value. Modern software development has taught us that development doesn’t end with production. Systems must be monitored to ensure they are meeting the needs of the business, even as that business shifts and changes under market pressures. Machine Learning is no different. In fact, models must be reviewed and maintained in some type of regular cadence. Unlike software, that is relatively static in nature, an ML model is code with data. As data changes, so must the model. It is an evolving system and must be observed and maintained even after production deployment.
  3. Scaling is one of the big problems of ML. It’s fairly easy to monitor one or two models in production manually, but once you scale to hundreds, even thousands of models, you will need systems in place to support the required maintenance of models.
  4. Maintenance is another thing to consider. Models must be updated. Sometimes many times a day. This means a delivery pipeline from initial hypothesis to production that is fast, scalable, and includes all the required tests and metrics gathering systems needed to monitor and control the lifecycle of the model.

The Machine Learning Lifecycle and Why It’s Challenging

I’m not going to dive into the Machine Learning Lifecycle in this article, but I will point out a few areas where that make it challenging to a manufacturer’s traditional IT department.

  • Data is a dependency. Very few ML models are of any value without a powerful data system to provide data for the learning portion of machine learning. Manufacturers often have data. Lots of data, in fact. Many manufacturers have been collecting telemetry data from operational technology for many years. But often that data is locked away in proprietary systems or behind multiple firewalls. There are tools to work with systems on-premises. Many data scientists are happy building experiments on their laptop. But this doesn’t scale to larger datasets or working with streaming data. Ideally, some type of lambda architecture will be needed to gather, prepare, and process the data for the machine learning process. Often, it’s preferred that this system be in the cloud where it’s accessible to entire teams and data engineers and leverage the compute power of the cloud to build and operationalize ML models.
  • Domain language issues. Data science brings a whole new set of tools and ideas to the traditional IT department. Data scientists are rarely software developers. They work in Notebooks and use programming languages like R, Python, and Julia. If you’re IT department isn’t used to the tooling and the processes of working with these tools, transferring from a Jupyter Notebook to an inferencing endpoint hosted on Kubernetes might be a challenge for your IT department.
  • Again, data scientists are not programmers. There are some who can program, but the code they tend to write is in support of training and testing ML models. It’s not generally written to be robust enough to standup to the type of software requirements demanded from a microservice. Your data scientists will likely need support from engineers who understand the deployment side of data science. You will need a team of people to help support your ML journey.

MLOPs and DevOps

MLOPs and DevOps do have a lot in common. They both focus on some of the same things, so if you already have a robust DevOps process in place in your organization, taking on MLOPs will be less of a challenge. However, if your IT department has never heard of DevOps, you might be in for a harder journey than expected.

  • DevOps is a proponent of automation. The idea is to reduce the friction from software development to production deployment by adding systems that automate the manual steps of the software deployment process. MLOPs has these same goals.
  • DevOps is a teams practice built on trust within the teams. This includes increased collaboration, communication, and an overall understanding from all the teams of the service life-cycle. Developers understand the requirements and rigors of operations and do their best to bake in what’s needed to support operations members of their team. Operations understand the business value of new features and systems and know how to monitor telemetry and systems to ensure risks are minimized. MLOPs has some of these same ideas, with an even greater emphasis on monitoring the model in production.
  • Both MLOPs and DevOps prioritize the concept of continuous deployment, experimentation, observability, and resilient systems.

The big difference between these two systems:

  • DevOps tends to deliver code
  • MLOPs delivers code and data

Use MLOPs to Reduce Risk

MLOPs can help protect you from risks associated with Machine Learning. As a practice, MLOPs encourages many of the same things that DevOps does, like teamwork, open and honest visibility into work, standard operating procedures, and a break in dependencies from traditional siloed IT operations.

  • Personnel dependency risks. What if your data scientist leaves the organization? Can you hire someone to take over that role?
  • Model accuracy can reduce over time. Without the systems in place to monitor models and the system in place to quickly deploy new models, you might find that you’re systems are compromised because they are delivering bad predictions or they are responding incorrectly to certain events.
  • What if there is a high dependency on the model and it’s not available? When systems are dependent on the accuracy of a model and that model isn’t available, could it bring production to halt? Or worse, put people’s lives at risk? These are all considerations that must be made when evaluating putting an ML Model into production.

Taking on MLOPs

MLOPS is not free. There are operational costs associated with the practice. This is not a cost you can avoid. Too much depends on the accuracy of your models, especially in a production environment to take on the risks without the assurances that a good MLOPs practice brings to manufacturers.

Here are the important things to remember:

  • Pushing a model to production is not a final step. It’s one step in the life-cycle of a model.
  • Monitor the model performance and make sure it’s meeting the accuracy requirements expected
  • Use Responsible AI practices
    • Intentionality
    • Accountability
    • Fairness
    • Privacy
    • Security
  • Again, MLOPs is not optional, nice to have, or an afterthought. If you are releasing models to production, you must start an MLOPs practice.