Page 9 - RC19 RealcommEDGE 2019 Fall Issue

While the Internet of Things (IoT) already has the ability to connect much
of our building operations into a smarter, more accessible network, we
expect the future of intelligent buildings to lean on IoT connectivity,
sensors, and other inputs informing aspects of artificial intelligence (AI)
such as machine learning, deep learning, and neural networks.

• AI – any technique that enables computers to AI may help manage specific decisions, but property
mimic human intelligence to learn from experience managers and engineers will keep ultimate control. It
• Machine Learning – a subset of AI that includes sta- also frees them up to spend more time managing tenant
tistical techniques to enable a computer to perform a satisfaction and running other building operations.
specific task more effectively as more data is received
• Deep Learning – a subset of machine learning If the last couple years of the innovation boom are any
generally based on neural networks capable of indication, it’s the path we’re heading towards. But what
learning from data that is unstructured or unlabeled does this mean for your bottom line today? Until the
• Neural Networks – informs deep learning by providing capital costs for some of these solutions come down,
a layered approach to processing information and it’s tough to get adoption. So, we recommend keeping
making decisions an eye on the technology of the future, but focus now
on opportunities for leveraging today’s technology to
At the heart of it, these solutions still rely on inputs and manage your portfolios more efficiently while mitigating
outputs and companies can make sense of it by looking risk and increasing asset values. Consider an incremental
at a hierarchy of needs. So you start with the questions: ‘crawl, walk, run’ approach.
1
What are you trying to solve? Is it reducing operational
expense, increasing tenant comfort, improving building Wherever the trends take technology in the future, the
efficiency or all the above? If so, what are the inputs that benefits of an energy strategy today are real, and leaders
impact these objectives? And how can I vary the inputs to will reap the benefits. The buzzwords are interesting, but
get a desired output? you can start answering important questions such as the
ones below that affect your operations without waiting
The roadmap to truly leverage AI in building system for next generation technologies:
solutions can bridge that gap between pre-determined
inputs and outputs toward true artificial thinking and even • How do I manage energy consumption more
autonomous building management. Neural networks effectively?
will take in specific data points like load, HVAC settings, • How do I increase my close rate while reducing costs?
external factors, financial data and energy sources. Then, • How do I streamline facility management?
through a set of hidden layers of decision-making that is
based on a system that can learn without any task specific Answering these questions will enable you to improve
rules, the output layer would manage both comfort and your business while preparing for the benefits AI will
cost. Imagine the future of building systems that can bring, and enable a better focus on exactly what you
monitor and interpret weather, account for seasonal want AI to accomplish in the future.
changes, understand how cloud cover might impact
radiant heat, calculate temperature based on how many Akshai Rao, a vice president at Yardi, is responsible for
employees showed up in the office that day, and more— the development of procurement and energy manage-
without any finite, specific inputs from a human source. ment solutions to ensure high-performing buildings.
Prior to Yardi, Akshai spent five years at Bain &
Don’t mistake the trend, AI in buildings will not replace Company where he focused on technology and telecom.
human intelligence any time soon—it will just help Learn more about the latest energy management technology at Yardi.
humans do their jobs better while software does the hard com/Pulse and increasing asset value through better facility manage-
work. For the foreseeable future, platforms leveraging ment at Yardi.com/Elevate.

1 Rogati, Monica, “The AI Hierarchy of Needs,” Hackernoon.com, June 2017. www.hackernoon.com/the-ai-hierarchy-of-needs-18f111fcc007

7