The Future is Now: AI’s Game-Changing Impact on Facilities Management

The Future is Now: AI’s Game-Changing Impact on Facilities Management

Welcome, facility dynamos and property visionaries! Buckle up because we’re embarking on a thrilling ride into the future, where Artificial Intelligence (AI) is not just a buzzword but the backbone of revolutionary facility management. It’s here to stay and is reshaping our world in ways we’re just beginning to grasp. So, let’s dive into the top ways AI will transform facilities management in the next five years, packing our journey with insights and, of course, a bit of fun. 🚀


1. Predictive Maintenance: The Crystal Ball of Facility Management

Remember when maintenance schedules were as unpredictable as a game of bingo? Those days are behind us. AI, with its predictive prowess, is turning maintenance into a science fiction-like narrative, where machines alert us about potential issues before they even occur. Imagine receiving a notification that your HVAC system will fail in two weeks unless a specific component is replaced. That’s not magic; it’s AI-driven predictive maintenance. This crystal ball capability means less downtime, reduced costs, and a big sigh of relief for facility managers everywhere.

2. Energy Optimization: AI, The Green Warrior

In an era where going green is not just a choice but a necessity, AI emerges as the champion of energy efficiency. Through real-time data analysis and learning from usage patterns, AI optimizes building energy consumption without compromising comfort. It adjusts lighting, heating, and air conditioning based on occupancy and even weather forecasts, slashing utility bills and carbon footprints. Picture this: your building not just consuming energy, but doing so with the wisdom of an eco-savant. That’s the power of AI in action.

3. Enhanced Security: AI as the Watchful Protector

Gone are the days when security meant bulky cameras and sleep-deprived guards. Enter AI: the smart, watchful protector that never blinks. AI-powered surveillance systems can now identify unusual activities, recognize faces, and even detect potential threats before they manifest. But it’s not just about keeping intruders out; it’s about ensuring a safe, secure environment for everyone inside. AI’s vigilant eyes augment our security measures, making our facilities as secure as Fort Knox, but with a lot more intelligence.

conductor of digital symphony

4. Seamless Automation and Integration: The AI Symphony

Imagine orchestrating a symphony where every instrument is a different building system, from lighting to HVAC to security. AI is the maestro, harmonizing these systems in a seamless performance of efficiency and convenience. It enables diverse systems to communicate and collaborate, creating an integrated, intelligent ecosystem. This automation not only enhances operational efficiency but also elevates the user experience, making buildings more intuitive and responsive to the needs of those within.

5. Intelligent Space Management: AI as the Space Guru

Space, the final frontier—especially in urban settings where every square foot counts. AI steps in as the ultimate space guru, optimizing the use of available space and adapting to changing needs through smart layout planning and usage analysis. It’s about making the most of what we have, whether it’s reconfiguring layouts for better flow, maximizing occupancy without overcrowding, or even predicting future space requirements. AI makes spaces not just smarter, but more adaptable and efficient.

6. Advanced Tenant Services: AI as the Ultimate Concierge

Welcome to the era of AI-powered tenant services, where AI acts as the ultimate concierge, enhancing tenant experience through personalized services and interactions. From voice-activated controls and intelligent assistance to predictive maintenance that ensures everything works perfectly, AI is elevating the standard of tenant services to unprecedented levels. It’s about creating environments where tenants don’t just reside or work; they thrive.

hooded figure casting spell

7. Data-Driven Decision Making: AI, The Insight Wizard

In facilities management, knowledge isn’t just power; it’s the key to innovation, efficiency, and sustainability. AI transforms vast oceans of data into actionable insights, guiding decisions from operational changes to strategic investments. It’s like having an insight wizard at your disposal, turning data into a roadmap for future-proofing your facilities and ensuring they not only meet the current needs but are also ready for what’s next.

8. The Evolution of Facility Management Roles: AI as the Catalyst

As AI reshapes the landscape of facilities management, it also redefines the roles within it. Facility managers evolve into tech-savvy strategists, leveraging AI tools to make smarter decisions and lead their teams. This shift emphasizes the importance of upskilling and embracing technology, ensuring that the human element in facility management grows alongside its AI counterparts.

Conclusion

As we step boldly into an AI-enhanced future, remember, the essence of facilities management is not just about maintaining spaces but evolving with them. The next five years will revolutionize our roles, making us not just caretakers but pioneers at the forefront of technological innovation. Embrace AI as the transformative force it is, and let’s lead our buildings into a smarter, more efficient, and sustainable future. The journey is just beginning, and the possibilities are endless. Here’s to shaping the future of facilities management together—smartly, sustainably, and with AI by our side.

The Pros and Cons of Building Automation Systems

The Pros and Cons of Building Automation Systems

Building automation systems (BAS) or “smart buildings”, are increasingly popular in commercial and industrial buildings. Why? Because they improve energy efficiency and reduce costs by integrating and automated systems such as lighting, HVAC, and security. While these systems of systems are often associated with larger commercial or industrial facilities, advances in technology are lowering price points enough for smaller building owners to access the benefits. But before you invest, consider the pros and cons of a building automation system.

What is an Building Automation System?

Building automation systems use a combination of sensors, controls, and algorithms to monitor and manage building systems. These systems can be integrated with a building’s existing infrastructure, such as HVAC and lighting systems, to create a centralized control system that can adjust and optimize building operations in real time. For example, a BAS can automatically adjust the temperature and ventilation in a building based on occupancy levels and outside weather conditions or turn off lights in unoccupied areas to reduce energy waste.

rooftop air handling unit

Building Automation System Pros

Automated building systems have the potential to significantly improve energy efficiency, reduce costs, and improve building comfort and productivity.

Greater Energy Efficiency

AS can use occupancy sensors and time schedules to control lighting and HVAC systems, ensuring that they are only running when needed and at optimal levels. By reducing energy usage during periods of low occupancy, such as nights and weekends, a BAS can help to significantly reduce energy costs.

Better Occupant Experiences

By optimizing building systems for comfort, such as temperature and lighting, BAS can help to create a more comfortable and productive work environment. This can lead to improved employee satisfaction, reduced absenteeism, and increased productivity.

Reduce Maintenance Repair and Costs

By continuously monitoring and optimizing building systems, a BAS can identify and diagnose issues before they become major problems, allowing for timely maintenance and repairs. This can help to extend the lifespan of building systems, reduce repair costs, and minimize downtime.

Real-time Analytics

One key feature of a BAS is its ability to provide real-time monitoring and data analytics. By collecting and analyzing data from building systems, such as energy usage and occupancy levels, a BAS can help building owners and managers identify areas of inefficiency and opportunities for improvement. This can help to inform future decisions around building upgrades, retrofits, and maintenance, allowing building owners and managers to optimize their operations and save money over the long term.

Energy Regulation Compliance

With energy codes and regulations becoming increasingly stringent, it is becoming more important for building owners and managers to optimize their energy usage and reduce waste. By implementing a BAS, building owners and managers can demonstrate their commitment to sustainability and energy efficiency, and potentially qualify for tax credits and other incentives.

medium-sized office building

Building Automation System Cons

Despite the many benefits of automated building systems, there are some potential drawbacks to consider.

Upfront Costs

Building owners may need to invest a significant amount of money to purchase and install the necessary hardware and software to create a fully integrated BAS. This cost can be a barrier for some building owners, particularly for smaller facilities with limited budgets.

Complex Installation

Building owners may need to work with a team of engineers and technicians to design, install, and configure the system, which can be time-consuming and require specialized expertise.

Technical Issues

While BAS systems are designed to be reliable, there is always a risk of technical issues and system failures. These issues can cause downtime and disrupt building operations, which can be costly and frustrating for building owners and occupants.

Staff Training

Adopting a BAS may require building owners to train their staff on how to use the new system. This can be time-consuming and may require additional resources to ensure that staff members are properly trained and understand how to use the system.

Security Concerns

As with any technology, there are potential security concerns with adopting a BAS. Building owners need to ensure that the system is properly secured and protected against cyber threats, as a security breach could have serious consequences for building operations and occupant safety.

While there are pros and cons to adopting an automated building system, building owners and managers should also consider the effects their decisions have on broader issues like climate change. Buildings make up an enormous amount of the world’s energy use and green house gas emissions. Reducing emissions takes collective action. Lower your building’s carbon footprint is doing your part.

AI vs Machine Learning: What’s the Difference?

AI vs Machine Learning: What’s the Difference?

AI and machine learning (ML) are often used interchangeable, but they’re not technically the same thing. However, the difference is smaller than you think, and once you understand it, you’ll never mistake the two again. The following is a very basic explanation and omits many technical aspects of AI and ML which go beyond the scope of the intended audience. The definitions and examples attempt to lay a foundation for further exploration around these topics.

Artificial Intelligence: The Entire Robot

Artificial intelligence (AI) is a broad term that refers to creating machines that can perform tasks that normally require human intelligence. Examples of such tasks include visual perception, speech recognition, decision-making, and language translation. There are many subsets and subfields of AI, each of which tries to solve a specific problem and/or takes a different approach to creating “intelligence”. Here are the five most recognized subsets of AI:

  1. Natural Language Processing (NLP) focuses on enabling machines to understand, interpret, and generate human language. NLP is used in applications such as chatbots, voice assistants, and language translation. ChatGPT is an NLP.
  2. Computer Vision is concerned with enabling machines to interpret and understand visual data from the world around them. Computer vision is used in applications such as object detection or facial recognition. Autonomous vehicles, like some Tesla models, use computer vision.
  3. Robotics develops machines that can physically and autonomously interact with the world around them to perform tasks like assembly line work or rescue operations. Boston Dynamics focuses on robotics.
  4. Expert Systems are designed to mimic the reason-based decision-making ability of an expert in a particular field, such as medical diagnosis or financial analysis. Expert systems are why you keep hearing about AI lawyers defending people in court.
  5. Machine Learning involves feeding data into a machine learning algorithm and allowing it to learn from that data in order to make accurate predictions or classifications about new data.

So, ML is a subset of AI. That’s the first big difference to note. While AI is a term that encompasses a wide range of technologies and techniques, ML is a specific approach to building AI systems.

It’s helpful to think of AI as the “entire robot”—a fully autonomous machine capable of thinking and acting like a human. However, each subset is only one part of the entire robot. Robotics attempts to develop the “body” for interacting with the environment. Computer vision gives the robot the ability to make visual sense of its world. NLP arms it with the power to communicate. ML bestows the faculty of learning. And expert systems send it to university. It’s a true Frankenstein’s monster of disparate parts, but when brought together will finally realize the goal of AI.  

What’s Machine Learning?

You hear a lot about ML because it’s a critical step in creating the entire robot. Almost everything we consider to be alive must be able to learn. Birds do it. Bees to it. Heck, even amoebas do it. But despite its ubiquity in the world of the living, learning is incredibly complex. Therefore, ML is taking on one of the biggest challenges, but it’s a triumph that offers the biggest ROI. Once we create a machine that learns, we can train it to make better decisions. So how do you create a machine to learn?

ML uses statistical algorithms to enable machines to learn from data and improve their performance on specific tasks over time. ML algorithms analyze large amounts of data to identify patterns, which it uses to make predictions or decisions on new data. Like humans, ML is a process that requires that machines be “taught” by exposing them to information.

ML Example: House Price Estimator

Suppose you wanted to create a ML learning algorithm that predicts the price of a house based on its size and location. You would need two sets of data: a training set and a test set. First, we create a training set of data composed of recently sold houses with their sale price and location.

The ML then processes the training data to look for patterns. After some processing, let’s say it “learned” the following “rules”:

  1. Houses larger than 2,000 sq ft sell for > $200K
  2. Houses less than 2,000 sq ft sell for < $200K
  3. Houses within 5 miles of the airport sell for < $100K
  4. Homes within 5 miles of the lake sell for > $300K

The algorithm could then use this knowledge to predict the price of a house outside the training dataset (i.e., the test set). For example, a house that is:

  • 2,500 sq ft and 3 miles from airport.

Since the new house is more than 2,000 sq ft, the algorithm would then apply the “> $200K” rule, but since the it’s also less than 5 miles of the airport, it would apply the “<$100K” rule. Therefore, the algorithm’s prediction would likely be “$150K”.

Three house prices with one predicted by AI

Next, the ML algorithm checks its guess against the actual price, which is $170K. It now has a $20,000 discrepancy it needs to resolve. It checks for more patterns and learns that, as houses of equal size get closer to the airport, they decrease in price. Through some calculations, the program can determine the changes in price by proximity and apply the data as a weighted value in its next prediction. For example, maybe each mile closer to the airport equates to a 10% decrease in price.

The machine uses this constant process of guessing and checking (called backpropagation) to improve its predictions. The more iterations and inputs, the “smarter” the algorithm gets.

“So what?”, you might ask, “Isn’t this simple logic? Why do we need a machine to do this?” Well, for one, ML can sift through data, find patterns, and test its guesses against real world data at an astonishing rate. In short, it can “learn” much quicker than humans. For another, it can juggle many more parameters than we ever could, so its guesses will inevitably we more accurate over time.

Think about all the factors that go into the price of a house besides size and location. There’s the house’s age, condition, number of rooms, the market conditions, and seller motivation just to name a few. But there are other less typical considerations like current interest rates, lot locations, or roof type. When you drill down further, you find that the real number of factors is enormous. Few sellers place a critical role on the color of a house when calculating an asking price, but what if it mattered more than we thought? What about the history of the house or the future of the neighborhood where it resides? The better our predictive capabilities, the more important these “lesser” considerations become.

ML can iterate much faster and with greater detail than we can, making it more efficient at locating “hidden” patterns. What if dark-colored houses sold for higher prices than light-colored ones? Maybe houses with more east-facing windows were cheaper than more west-facing ones. Machine learning can consider all these factors and then some—and do it in real time.

Finally, imaging adding to this learning algorithm the ability to search for, monitor, and collect house price information for a large region of the country. It would be a fully autonomous learning and predicting machine that would only get smarter the longer it worked. That’s where ML is at today.

Conclusion

It’s easy to see how ML learning algorithms are a game changer for humanity. Their application to knowledge-based work of every kind is almost limitless. What’s AI developers are attempted is the automation of thinking itself. Translate these advantages to building automation, and it’s easy to see how ML will transform the built environment. Imagine AI that could plan your building’s HVAC setpoints a week in advance based on a weekly weather forecast and price predictions for energy costs. What about a FDD system that could predict chiller failure with 98% accuracy?

IT vs OT Systems: What’s the Difference?

IT vs OT Systems: What’s the Difference?

Information Technology (IT) and Operations Technology (OT) are two distinct yet interconnected fields that play critical roles in modern organizations. IT deals with the use of technology to support business processes, while OT focuses on the use of technology to control and monitor industrial and commercial processes in facilities. By looking at IT vs OT systems, it’s easy to identify their major differences.

What are IT Systems?

IT systems are primarily used to support business processes, such as data storage, processing, and communication. These systems include things like enterprise resource planning (ERP) systems, customer relationship management (CRM) systems, and enterprise-wide networks. They are responsible for maintaining the flow of data within an organization, and provide important services such as email, file storage, and data analysis. IT systems are also responsible for maintaining the security of an organization’s data, including firewalls, intrusion detection systems, and encryption.

What are OT Systems?

OT systems, on the other hand, are used to control and monitor industrial processes. These systems include things like programmable logic controllers (PLCs), distributed control systems (DCSs), and supervisory control and data acquisition (SCADA) systems. They are responsible for controlling and monitoring the physical processes within an organization, such as manufacturing processes, power generation, and water treatment. OT systems are designed to operate in real-time and are often required to operate 24/7.

When we look at IT vs OT systems, trends show they are increasingly being integrated to improve the overall efficiency of companies and facilities. For example, a building owner might use data from an OT system to optimize their HVAC systems, or an energy company might use data from an IT system to identify and respond to potential power outages.

diagram showing and IT system components vs  OT system components
The difference between IT and OT system components. Note that IT and OT must interface with one another.

Network Security

One of the major differences between IT and OT is in the level of security required. IT systems are typically more connected to the internet; hence they are more exposed to cyber threats. These systems need to comply with industry-specific standards like the Payment Card Industry Data Security Standard (PCI-DSS), HIPAA and SOC2. Organizations need to maintain regular backups, have intrusion detection and prevention systems, as well as have strong and regularly updated access controls in place.

OT systems on the other hand, are typically more isolated from the internet and have fewer connections to external networks. These systems need to comply with standards like IEC 62443 which are specific to industrial environments. Because of the real-time nature of their operations, organizations need to have redundancy in place and maintain backups that can be restored within minutes, have detailed incident response plans, as well as maintain physical security of the systems.

Conclusion

IT and OT systems play critical roles in modern organizations, with IT systems primarily focused on supporting business processes and OT systems focused on controlling and monitoring industrial processes. The two fields are becoming increasingly integrated, with organizations leveraging data from both types of systems to improve overall efficiency. However, they are also vastly different in terms of the level of security required, with IT systems being more exposed to cyber threats, and OT systems being more isolated and needing to comply with industrial specific standards.

BACnet Basics: What are Device Profiles?

BACnet Basics: What are Device Profiles?

In this article in our BACnet Basics Series, we look at Device Profiles, why they’re important and how they’re created. We’ve also included a real world example that illustrates how to use device profiles to accurately specify your own projects.

What are Device Profiles?

As we saw in BACnet Basics: What are BIBBs?, device functions come in five basic categories, each containing specific capabilities. For example, the category Data Sharing (DS) includes capabilities like Read Properties (RP), Write Properties (WP) or Change of Value (COV). If we combined all these services into a minimum collection of capabilities, we would be creating a device profile.

As an analogy, think of the profile “Automobile”. Every machine that claims to be an “automobile” needs the functions of Acceleration (A), Deceleration (D) and Maneuverability (M). Of course, there can be automobiles that do much more, but every “automobile” must, at minimum, perform these three functions (A,D,M).

Definition: BACnet device profiles define the minimum set of BACnet Interoperability Building Blocks (BIBBs) supported by a device claiming that profile. When a device claims a specific profile, you know that it contains a preset of specified functions and services. Profiles are handy because they provide a short-hand method for describing a device and its interoperability capabilities. Device profiles are organized into Groups and Families

Device Groups

Device Groups are general categories of device functions. There are four Group types:

  1. Operator Interface—Covers the minimum capabilities for workstations and other user interface devices. Devices normally support A-side (Client) functionality.
  2. Controller Device—Covers anything from programmable building controllers to smart sensors. Devices normally support B-side (Server) functionality, but more advanced supervisory controllers also include A-side (Client) functionality.
  3. Control Station—Covers lighting control stations that are smaller client devices that support specific user controls such as manual light switches.
  4. Basic Device—Covers all “miscellaneous” family functionality. Usually included alongside other device profiles.
Table showing bacnet profile groups

Device Families

Each Profile Group contains various Families within it. Families cover profiles for various, supported building systems like Lighting, Life Safety, and General Purpose. For example, the Controller Device Group contains profiles for the following Family types:

(Example) Controller Family

  • General Purpose—General purpose controllers usually for HVAC and lighting.
  • Access Control—Access control controllers such as an access control panel
  • Lighting—Lighting controllers such as supervisory lighting controller
  • Life Safety—Life safety controllers such as a fire detection panel.
  • Elevator—Elevator controllers

Let’s zoom into the General Purpose profile family within the Controller Device Group and see what BIBBs it contains.

  • Building Controller (B-BC) —Field programmable and configurable supervisory controllers in HVAC and general purpose application.
  • Advanced Application Controller (B-AAC)—Controllers that run advanced HVAC or general purpose control applications.
  • Application Specific Controller (B-ASC)—Controllers that run specific HVAC or general purpose control applications.
  • Smart Actuator (B-SA)—Small, commendable actuator devices.
  • Smart Sensor (B-SS)—Small sensors that provide sensor values to other devices.

BACnet device profile Families are organized in a container hierarchy. As you move up in complexity, you increase the minimum amount of BIBBS required. Like nesting dolls, each profile contains all the minimum profiles from the previous ones. 

For example, the above General Purpose BACnet profiles increase in complexity as you move up from Smart Sensor to Building Controller. All BIBBS included in a Smart Sensor profile are always included in a Smart Actuator profile, and all the BIBBs included in those two profiles are always included in an Application Specific Controller, and so on.

List of general purpose controller bacnet profiles

Although higher level BACnet profiles contain more BIBBs, it’s not the number of profiles that matters. Each profile requires a minimum number and type of profiles. So, even if a device contains or exceeds the minimum number of BIBBs, it doesn’t guarantee it will meet the standard. It must contain the minimum number of the correct BIBBs to meet the profile standard.

Specifying Device Profiles: Boardroom Example

Let’s use the Device Profile Quick Reference Guide to see an example of how to choose the device profiles for a real-world project. Read the following scenario:

  • You want to outfit a medium-sized boardroom equipped with a control panel with a built-in controller. The panel will control the room’s temperature and lighting. You also need manual lighting controls near the door. 

To determine the device profiles needed for the project, we can start by listing the functionality we need. We will need HVAC controls for temperature. For lighting, we will need controls for both the panel and a manual user control switch on the wall. Therefore, we will need functionality from the Controller Group and Control Station Group.

Next, we can determine what Families we need within each group.

For the Controller Group, we need:

  • General Purpose Family for HVAC
  • Lighting Family for panel control lighting
  • Access Control Family for access

For the Control Station Group, we need:

  • Lighting Family for manual switch lighting control

Finally, we can choose specific profiles to fulfill our HVAC and lighting functionality.

bacnet touch screen device for a boardroom.

HVAC Profiles

In the Reference Guide, we see the following profiles for the General Purpose Controller Family:

  • B-BC: The building controller is intended for field programmable and configurable supervisory controllers in HVAC and general purpose applications.
  • B-AAC: The advanced application controller is intended for controllers that run advanced HVAC or general purpose control applications. It does not require being configurable through BACnet.
  • B-ASC: The application specific controller is intended for controllers that run specific HVAC or general purpose control applications. It does not require being configurable through BACnet.
  • B-SA: The smart actuator is intended for small actuator devices that allow being commanded.
  • B-SS: The smart sensor is intended for small sensor devices that provide sensor values to other devices.

We can ignore the last two profiles, because we need neither actuators (B-SA) or sensors (B-SS) for the project. We can also eliminate the Building Controller (B-BC) profile because it does not require supervisory control. Depending on our HVAC needs, we could choose either the Advanced Application (B-AAC) or the Application Specific (B-ASC) profile.

Lighting Profiles

In the Reference Guide, we see the following profiles for the Lighting Controller Family:

  • B-LS: The lighting supervisory controller is intended for controllers in lighting applications that can command and operate subordinate lighting controllers, in particular through group write commanding.
  • B-LD: The lighting device is intended for lighting controllers that control individual lights or groups of lights. Normally used as leaf nodes in lighting group setups.

We would choose the B-LD profile if the panel only controls one group of lights. However, if the lighting is more complex, we might opt for the B-LS with supervisory controls.

Control Station Profiles

Because the room also requires manual user lighting controls, we need a profile from the Control Station Family. In the Reference Guide, we see the following profiles:

  • B-ALCS: The advanced lighting control station is intended for sophisticated control stations that support user view, control and limited configuration of lighting functionality. Provides full commanding support of lighting objects and group operations for them.
  • B-LCS: The lighting control station is intended for control stations that support simple control of lighting functionality and limited status indication. Provides limited support of commanding lighting objects.

The simpler B-LCS would work for this project. But, again, depending on the complexity of the room’s lighting, we might choose the more complex profile.

Conclusion

Through the Boardroom Example above, we can see how BACnet profiles make project specifications easier and more accurate. Standards and profiles support an accurate procurement process, requiring less change orders and adjustments. Defining capabilities also creates an outcomes-based workflow so that buildings function the way owners and tenants need them to.