Control & Automation
FeaturesMechanical & Plumbing
Dynamic VAV Optimization, machine learning and AI: Advances in building control
By Mark Byvelds and Natalia Malafeeva
“The rise of digitalization may bring with it changes in skillsets for building operators [...] but the core demands of the role are still present.”
By Mark Byvelds and Natalia Malafeeva
September 24, 2021 – We have arrived at the next stage of building control. Moving from pneumatic to DDC (direct digital control) represented a major shift in control equipment and, more importantly, in the feedback coming from building systems.
This next stage—the application of machine learning and artificial intelligence—builds upon DDC to use that feedback for better control. What does better control mean?
First, it meets the needs of the building and its occupants. Rather than reacting to a space becoming warmer than desired, the control system can predict it will become warmer than required, and make the necessary adjustments before occupants become uncomfortable.
Second, it is more efficient. Setpoints change constantly based on current or upcoming demand, meaning building systems deliver what is needed at the moment it is needed—and nothing more.
What’s wrong with my BMS?
The first question for many may be Why?. What is it that AI and machine learning can do that a modern BMS (building management system) cannot?
The number one answer is adaptability. Machine learning crunches massive amounts of data—better than any person possibly could—to help us understand the complex dynamics of a specific building. This understanding allows spaces to be conditioned based on what is actually needed as opposed to what we think is needed, especially as the use and occupancy of a building changes over time.
An AI approach also allows for a more efficient and cost-effective BMS setup. Rather than programming complex, multi-variable strategies for every building, a common cloud-based AI model can be applied to an unlimited number of buildings.
Fault tolerance can also play a significant role. Even a great piece of energy-efficient programming can repeatedly stumble. An example: a temperature sensor receiving direct sunlight in the afternoon which causes the trim & respond static pressure reset to fail time and time again as one zone thinks it needs more cooling than actually required. The result is missed energy and cost-saving opportunities. Machine learning will identify this pattern of failure; it will flag the issue for investigation and learn to ignore this sensor from the overall strategy, thereby allowing energy savings to be achieved.
When answering the Why?, one should also consider the Why not? use AI and machine learning. Depending on the facility, bi-directional internet access to a cloud platform may not be an option. In this case, an on-premises solution would be needed, which may be fine, or may be cost-prohibitive.
The traditional cost/benefit analysis stands true, as well: what is AI offering for a given building that existing control infrastructure cannot achieve?
In a practical sense, the Why not? may also be related to fear… fear of losing control over a building or, as a building operator, fear of losing your job.
While understandable, these fears are unfounded. Any AI-based solution needs to have local oversight to allow the building operator to see how systems are being controlled, and to step in and override or disable systems if they become truly concerning.
Building operator roles may change, but certainly won’t go away. The rise of digitalization may bring with it changes in skillsets for building operators (the ability to support growing connectivity between devices and work with multiple platforms), but the core demands of the role are still present.
Mechanical infrastructure still needs to be maintained; it will just become demand-based rather than time-based. Efficiency opportunities still need to be evaluated, and technology will help inform us where to look.
Case study – Dynamic VAV Optimization
Thus far, the focus of Siemens Smart Infrastructure—as it relates to AI in building HVAC control—has been on variable air volume (VAV) systems. VAV systems are commonplace throughout the commercial and institutional sector, meaning there are numerous opportunities for achieving better results through the application of machine learning and artificial intelligence.
This particular solution is called Dynamic VAV Optimization (DVO), and it leverages a building’s existing data sources and control infrastructure to make better decisions.
But what is a better decision? In short, it depends on the priority: users are able to select operation in Green Mode to prioritize comfort and energy efficiency, or Defence Mode to prioritize airborne viral transmission risk reduction. Users can also disable DVO and return to the system’s base programming or manual override if needed.
Green Mode overcomes many of the VAV Optimization challenges with which conventional BAS strategies struggle: multivariable decision-making, forward prediction, and fault tolerance, to name a few. Using existing control hardware in the building, the end result has been a roughly 25% energy savings in systems without an existing pressure reset strategy, and a 10% reduction in systems that have one.
Defence Mode allows for a central strategy to be defined and easily updated so that all sites running DVO are capable of deploying the latest recommendations from ASHRAE and CDC (Centers for Disease Control & Prevention).
Currently, this is a balance of fresh air changes, maintaining target humidity and space temperatures and, in many cases, increasing them compared to conventional setpoints.
AI really shines when conditions are not ideal, as when a building is struggling to maintain target humidity in the winter; increasing fresh air ventilation is likely to further lower indoor relative humidity, yet higher air change rates are helpful for lowering risk. In a scenario like this, AI logic can determine the lowest-risk point for balancing these ever-changing factors, whereas a person or BMS simply cannot.
Regardless of the mode, DVO allows AI to handle these challenging decisions, then send simple setpoint commands to the BMS so that it can do what it does best.
Dynamic VAV Optimization was recently deployed in the office space of a critical facility in Toronto, which has remained open and partially occupied throughout the Covid-19 pandemic. In this case, the strategy is to operate the system in Defence Mode to mitigate transmission risk, then switch to Green Mode as soon as it is deemed safe to do so.
The application of machine learning—in which a database is built to help the engine understand how zones within the building react to ventilation changes and differing environmental conditions—allows for setpoints to be adjusted dynamically based on what is currently the optimal approach. When in Defence Mode, this takes into account total air changes, outside air volume, filtration, space temperature and relative humidity, as well as constraints of the ventilation system, such as heating, humidification and airflow capacity.
In Green Mode, the machine learning application adjusts static pressure and supply air temperature based on conditions in each VAV zone to rapidly drive down energy consumption as much as possible while still meeting the space requirements. By knowing how the building will react in upcoming weather conditions, it will seek out the lowest total energy consumption for fan power, heating, cooling and re-heating, and do so proactively.
With all of these variables at play, and “best case” conditions changing regularly, it is easy to see where machine learning can fit into building control.
This approach meets the near-term need of risk management needs while also supporting the facility’s long-term goals of reducing energy consumption and emissions.
Although the system is operating in Defence Mode, both Green and Defence modes were tested during commissioning of the technology. Results during the commissioning process have shown an average reduction in AHU (air handling unit) static pressure of 57% while maintaining airflow requirements to terminal units, resulting in an average fan power reduction of 35%, and delivering a pro-rated annual benefit of 126,000 kWh (approximately $19,000 and 3.8 t CO2e) across the five AHUs.
As we seek to further reduce energy consumption and move forward on sustainability targets, it is absolutely necessary to use energy wisely. Have you considered how new approaches to control can benefit your buildings, projects or customers? Artificial intelligence and machine learning solutions for HVAC control are here now and growing rapidly, and can be deployed in both existing buildings and new construction.
Mark Byvelds, P.Eng, CMVP, is a registered Professional Engineer in Ontario and the national business development manager for Energy Services with Siemens Canada Ltd. With over 10 years of experience in the energy management and sustainability sector in Canada and the U.K., he has supported both large and small energy projects, with a keen interest in deploying the latest technologies to better operate our built infrastructure.
With over 10 years of experience, Natalia Malafeeva, M.Eng, CEM, CMVP, is a dedicated energy expert with success in promoting and implementing energy optimization and Existing Building Commissioning projects. She has spent the last nine years working with building automation controls providers, which allows her to tap into the world of building controls and associated systems’ operational improvements. In her current role, Natalia is responsible for the operations of the Energy Engineering team to support the development and execution of energy projects.