Demand for smart home and industrial IoT

Market trends and analysis point to steep growth in the IoT industry, particularly in the industrial IoT segment. The 2020 Mordor Intelligence report Smart Homes Market – Growth, Trends, COVID-19 Impact, and Forecasts (2021-2026) projects the smart home market to grow from $79 billion US Dollars (USD) in 2020 to reach $313 billion by 2026. Similarly, the 2019 Grand View Research report Industrial Internet Of Things Market Size, Share & Trends Analysis Report By Component (Solution, Services, Platform) By End Use (Manufacturing, Logistics & Transport), By Region, And Segment Forecasts, 2019-2025 projects the industrial IoT market to grow from $214 billion in 2018 to reach $949 billion by 2025. In both studies, the estimated compound annual growth rate (CAGR) is approximately 25-30%. That means there are big opportunities for new products, solutions, and services to find success with businesses and end consumers.

You can see a depiction of market forecasts for smart home and industrial IoT here:

Figure 1.7 – Market forecasts for smart home and industrial IoT

It's important to keep in mind that forecasts are just that: forecasts. The only way those forecasts become reality is if inventors and problem solvers such as you and I get excited and make stuff! The key to understanding the future of smart home and industrial IoT solutions is how they are influenced by the value propositions of complete edge-to-cloud patterns and local ML inferencing. We can reflect on the key benefits of bringing ML to the edge to see how solutions in these markets are ripe for innovation.

Smart home use cases

In smart home solutions, the standard for functionality is oriented around environmental monitoring (temperature/electrical consumption/luminescence), automating state changes (turn this on in the morning and off at night), and introducing convenience where it was not previously possible (turn on the air conditioning when you are on your way home).

The primary persona using the product is the end consumer who lives in the residence where the solution is deployed. Secondary personas are guests of the owner, pets, public utilities, and home security service providers. At the product design level, the chief stakeholders are the IoT architect, security engineer, device manufacturer, and data scientist. Smart home products have been exploring and enjoying critical success when tapping into the power of AI and ML hosted in the cloud.

Here are three ways that deploying ML capabilities to the edge can benefit smart home use cases:

• Voice-assisted interfaces: Smart voice assistants such as Amazon's Alexa rely on the cloud to perform speech-to-text routines in order to process commands and generate audio responses. Running speech recognition models at the edge can help keep some common commands available for consumers even when the network is unavailable. Training models for recognition of who is speaking and incorporating that in responses increases the personalization factor and could make these voice assistants feel even more believable.
• Home security: Recognizing a breach of security has traditionally relied on binary sensors such as passive infrared for motion or magnetic proximity to detect open doors and windows. This simple mechanism can lead to false positives and undetected real security events. The next level of smart security will require complex event detection that analyzes multivariate inputs and confidence scores from trained models. Local models can evaluate whether the consumer is home or away automatically, and the solution can use that to calibrate sensitivity to events and escalate notifications of events. Video camera feeds are a classic example of a high data rate use case that becomes significantly cheaper to use with local processing for determining which clips to upload to the cloud for storage and further processing.
• Sustainability and convenience: Simple thermostats that maintain a temperature threshold are limited to recognizing when the threshold is breached and reacting by engaging a furnace or air conditioning system. Conventional smart home automation improves on this by reading weather forecasts, building a schedule profile of who is present in the home, and obeying rules for economical operation. ML can take us even further by analyzing a wider variety of inputs to determine via a recommendation engine how to achieve personal comfort targets most sustainably. For example, an ML model might identify and tell us that for your specific home, the most sustainable way to cool off in the evenings is to run the air conditioning in 5-minute bursts over 2 hours instead of frontloading for 30 minutes.

Industrial use cases

In industrial verticals such as manufacturing, power and utilities, and supply chain logistics, the common threads to innovating are creating profitable new business models and reducing the costs of existing business models. In order to innovate with the world of IT, these goals can be achieved through a better understanding of customer needs and the operational data generated by the business to test a new hypothesis. That understanding comes from using more of the existing data already collected and acquiring new streams of data needed to resolve hypotheses that lead to valuable new opportunities.

As per the 2015 McKinsey Global Institute report Unlocking the potential of the Internet of Things, only 1% of data collected by a business's IoT sensors is examined. The challenge to using the data is making it accessible to the systems and people that can get value from it. Data has little value when it is ingested at the edge but stored in an on-premises silo that can't afford to ship it to the cloud for analysis. This is where today's edge solutions can turn data into actionable insights with local compute and ML.

Here are three use cases for ML at the edge in industrial IoT settings:

• Predictive maintenance: Industrial businesses invest in and deploy expensive machinery to perform work. This machinery, such as a sheet metal press, computer numerical control (CNC) router, or an excavator, only performs optimally for so many duty cycles before a maintenance operation is needed or, worse, before they experience a failure while on the job. The need to keep machinery in top condition while minimizing downtime and expenses on unnecessary maintenance is a leading use case for industrial IoT and edge solutions. Training models and deploying them at the edge for predictive maintenance detection not only saves businesses from expensive downtime events but builds on the benefits of local ML by ensuring smooth operations in remote environments without high-speed or consistent network access.
• Safety and security: The physical safety and security of employees should be the top concern for any business. Safety first, as it goes. ML-powered edge solutions raise the bar on workplace safety with applications such as computer vision (CV) models to detect when an employee is about to enter a hazardous environment without the required safety equipment, such as a hard hat or safety vest. Similar solutions can also be used to detect when unauthorized personnel are entering (or trying to enter) a restricted area. When it comes to human safety, latency and availability are paramount, so running a fully functional solution at the edge means bringing the ML capabilities with it.
• Quality assurance: When a human operator is inspecting a component or finished product on a manufacturing line, they know which aspects of quality to inspect based on a trained reference (every batch of cookies should taste like this cookie), comparison to a specification (thickness, sheen, strength of aluminum foil), or human perception (do these two blocks of wood have reasonably similar wood grain to be used together?). ML innovates how manufacturers, for example, can capture the intuition of human quality inspectors to increase the scale and precision of their operations. With sensors such as cameras and CV models deployed to the manufacturing environment, it is feasible to inspect every component or final product (instead of an arbitrary sample) with a statistically consistent evaluation applied every time. This also brings a benefit to quality assurance (QA) teams by shifting the focus to inspecting solution performance instead of working on highly repetitive tasks dependent upon rapid subjective analysis. In other words, I'd rather QA a sample of 10,000 items passing inspection from an ML solution instead of every one of those 10,000 items. Running such a solution at the edge delivers on the key benefits of reducing overall data sent to the cloud and minimizing latency for the solution to produce results.

These use cases across smart homes and industry highlight the benefits that can be achieved with ML-powered edge solutions. Lofty forecasts on market growth in IoT are more likely to become reality if there are more developers out there bringing innovative new edge solutions to life! Let's review the smart home solution (and gratis product idea for someone out there to build) that will drive the hands-on material throughout this book.