Image default
Guest Articles

Transforming Commercial Real Estate with Artificial Intelligence – How Buildings Can Help Save the World

In 2021, with the election of President Biden and the United States’ reinstatement in the Paris Climate Agreement, American policies at the federal, state, and municipal levels will put pressure on organizations to invest in clean technologies and support climate change policies. These policies, certain to materialize in the coming months, will cause all sectors to place a greater emphasis on going green.

As such, businesses will need to evaluate how to adapt their business models to comply with new carbon reduction and other climate change policies.
Real estate, specifically commercial real estate, is one area where a large amount of energy is expended, causing federal and state rules and regulations to be continuously introduced. Many commercial real estate buildings are energy inefficient and aren’t currently taking steps to become more sustainable. So, what course of action should they take? 

In the built environment, HVAC (heating, ventilation, and air conditioning) systems are a great place to start as they account for approximately 51% of total energy usage in commercial buildings. These systems are very often inefficient, poorly maintained, costly to manage, lead to occupant discomfort, and produce a great deal of greenhouse gas emissions. We must do better. And with artificial intelligence (AI), we truly can.

As IoT technology advances, commercial HVAC systems are still, for the most part, fixed systems programmed for a static environment, even though weather, seasons, and tenant behaviors are fluid and dynamic. The built environment in general is significantly lagging behind other industries from an innovation and technological standpoint. In addition, energy efficient technology opportunities during the design phase are often value engineered out prior to the construction of the building due to budget constraints. 

So, what are the building optimization strategies that exist in buildings today?

Buildings today are typically controlled based on schedules of operation and setpoints. The schedules state when the building is typically occupied or unoccupied. When the building switches mode, the heating or cooling starts to bring the temperature towards comfort. The amount of heating or cooling provided into a space is proportional to the difference between the current and desired temperatures. When the operation mode is switched from unoccupied to occupied, suddenly, this difference becomes significant and the heaters/coolers are turned on to full capacity causing a peak in energy consumption. This reactive approach is one of the leading factors that makes HVAC systems so wasteful, both in terms of GHG emissions and utility costs. 

In a larger building, each room is controlled independently. If a room needs cooling, it triggers the cooling mode; if it does not, it stops the cooling. The same goes with the heating mode. Both modes are used as needed throughout the day and effort goes into ensuring the two remain balanced. Sometimes buildings end up reheating cool air resulting in energy wasted. Most buildings have rules with delays to ensure that this waste is minimized, which is a great start, but its only the tip of the iceberg.

Many other rules are written by expert operators to improve the efficiency of buildings, though they are static and need to be updated with time. Most rules also seldomly leverage external data such as weather and occupancy forecasts, which greatly impact a building’s thermal behavior, nor do they make use of dynamic electricity pricing. Hiring an expensive controls technician to improve the commissioning of the building does not guarantee savings, can be very time consuming, and the results are impossible to maintain as equipment settings drift with time.

All of these elements have led to the inefficiency of HVAC systems in buildings, which continue to contribute to higher energy bills and maintenance costs, while negatively impacting the environment. This is where AI can change everything.

Put simply, I can help optimize sustainable technologies, such as HVAC automation solutions, to make them as efficient as possible in an extremely scalable manner. In the real estate industry, it is important to note that each building is unique and modeling a software on a case-by-case basis is neither cost-effective nor scalable. However, AI-driven technologies have the advantage of interfacing with any building, allowing for autonomous learning of each building’s behaviors and their individual energy consumption patterns. There are hundreds of thousands of real-time data points, such as outside temperature, sun/cloud positioning, fan speed, duct pressure, heater status, humidity levels, occupant density and more that the AI uses to analyze and ultimately optimize HVAC systems. 

By using an AI model-based optimized method, we can explicitly state what we want to maximize (comfort) and minimize (cost and greenhouse gas emissions) and what are the limits to respect (equipment use/cycling). The ultimate benefit of AI being that it can enable impactful energy savings very rapidly (up to 25% in less than 3 months with some technologies and reductions in carbon footprint of 20-40%), which is a key part of the new legislation put forward by the new Biden administration. 

With the climate crisis reaching a critical turning point, time is a luxury we no longer have. It is vital to implement cost-effective, non-intrusive, quick to deploy, and scalable sustainable solutions like AI technology for HVAC to effectively reverse the damage caused to our climate before it is too late. Applying AI to HVAC is a low-hanging fruit that will enable real estate organizations to proactively comply with new policies while meeting their ESG goals in a faster than expected timeframe.

Related posts

Generative AI for Your Business: Can You Enjoy Both Customization & Short Time-to-Market?

Amit Ben

Cyberthreats spike during the holiday season. Here’s how your company should respond

Dr. Shaun McAlmont

Struggling with ROI in AI? A Lesson in Scale from AI Leaders

Alexis Fournier