I recently had the opportunity to participate in a webinar, hosted by Realcomm, focused on the use of artificial intelligence (AI) / machine learning in commercial real estate. I was part of a panel of industry speakers, and we each shared our insights into what AI can do for commercial buildings as well as obstacles and tips for implementation. Below are some key takeaways from the conversation. If you’re interested in learning more about this topic, I’d suggest to listen to the webinar recording.
The moderator used a live poll to gauge the listeners’ familiarity with energy management solutions based on AI. The responses were spread out across the spectrum —from beginning to pilot of the technology to no current plans to implement. To me this wasn’t surprising at all. In fact, the answer given to this question is most likely influenced by an individual’s definition of AI.
Some may hear the term AI —as it relates to energy management— and envision a fully autonomous building that doesn’t require an onsite facilities team. It’s important to underscore that this is not the case. AI solutions are meant to augment the role of a facilities team. For example, AI can be used as a tool to analyze data and get insights into building systems that would be previously unattainable. In fact, Artificial Intelligence (AI) and Machine learning (ML) systems are particularly well-suited for learning more about the relation between input and output variables without mathematical models; and being solely data-based we can then infer the best decision or action to be taken. However, AI and ML are not particularly suitable to translate that decision/action taken into a control command, for example low-level motion control of robot arms. By way of illustration, once you command the motion decided by AI/ML, the servo drive is going to try to close its velocity, position, acceleration, and torque PID (proportional–integral–derivative) loops in order to move in the commanded fashion. Within a building, the “low-level control”, is the loop within the BMS that take on the actual actions and keep everything operating as it should.
At BuildingIQ, we address this gap with human capital, one of the five pillars that support our 5i platform. This encompasses our expert team of remote data scientists, who provide an extra layer of support and monitoring to our platform, as well as the building’s onsite facilities team. The on-the-ground facilities team is critical as they know the nuances of their building, the tendencies of tenants, and other intangibles to be factored. Vendors need to take bigger steps to show that AI-based solutions will help communicate the importance of the facilities manager role by showing its impact with data.
Without AI, energy management solutions can often cause information overload. The complexity of buildings is often overlooked. The number of sensors and IoT-enabled devices providing various forms of data in a variety of formats can be daunting. Many industries run into this same problem where more data is collected that can be manually sifted through. This can lead to ignoring critical data. The underlying reason is that IoT, at its core, enables different components to communicate over the internet, without necessarily providing any decision-making capabilities. AI/ML provides the extra functionality of analyzing the data from the aforementioned components to reach a diagnosis. And, it is the diagnosis that truly adds value to the facilities teams.
In the end, machine learning and IoT complement, not compete with, each other. Together they can be the basis for providing services that help create operational efficiencies, reducing energy consumption, improving occupant experiences, achieving sustainability goals, and effectively optimizing financial performance.
AI can come in many different forms, which is true even within our own 5i platform. As the moderator on the webinar mentioned: AI is real, it’s happening. So, start small and scale.
Steve Nguyen is VP of Product and Marketing at BuildingIQ. He loves products and ideas that transform markets or society. Whether they are transformative in and of themselves, or because they are enablers, he’s driven by creating the stories, teams, and strategy that make these agents successful.