Addressing Today's Challenges In Commercial Buildings

Touch4IT logo
Martin
Mar 29, 2022
4 min read
Smart Commercial Buildings

In recent years, concerns about reducing carbon footprints and rising energy prices have increased interest in smart building solutions. According to various sources, the smart building market will more than double between 2018 and 2026. At the midpoint of this period, let’s address some of the challenges of effectively operating HVAC systems in modern office buildings.

Challenges

Together with lighting, HVAC (Heating, Ventilation, and Air Conditioning) systems represent the biggest energy consumers in the operation of office buildings. Modern buildings are designed to allow high-efficiency operation and to meet new standards and requirements. However, even the most efficient systems will not operate efficiently if not properly set up and maintained.

We believe that using machine learning techniques in Building Analytics software brings additional value to customers. Here are some examples:

1. Control inefficiencies

Even a modern hybrid car can consume a lot of fuel if the driver doesn’t operate it properly. The same applies to building HVAC systems.

Some BMS (Building Management Systems) manufacturers offer data analytics as a service: a dedicated expert team regularly acquires and analyzes seasonal data and provides recommendations, such as setpoint adjustments. We believe that this can be done automatically. We propose the following 3-step approach:

  1. Detection of control inefficiency with potential energy savings (e.g., if there is simultaneous heating and cooling without the need for dehumidification)
  2. Automated creation of summary reports, including specific action recommendations. Potential savings can be monetized and included in the report. This makes it more attractive for the building owner, with clearly visible added value.
  3. Once the Building Analytics software is integrated with BMS, setpoints can be calculated online using machine learning and optimization methods. The setpoints are adjusted automatically to provide immediate savings.

Faulty sensor readings also lead to inappropriate control strategies. Therefore, reliable detection of frozen or out-of-range sensors saves system operation. The figure below illustrates a typical air handling unit schedule, with sensor locations shown as red dots.

2. AFDD

For years, the building industry has moved toward introducing automated fault detection and diagnostics technology to enable predictive maintenance strategies. This is primarily because equipment deterioration causes higher energy consumption and increased costs. In today’s world, facility teams need remote visibility into building performance, combined with automated root-cause analysis of equipment issues. No one wants to send technicians on to the site unless they must. Moreover, with automated diagnostics (the second “D” in “AFDD”), service technicians can come to the site already equipped with all necessary tools and service parts - this again saves time and costs of the service. According to the US Department of Energy’s Operations & Maintenance Best Practices Guide, maintenance costs can be reduced by up to 30%. Applying the AFDD strategy enables building owners to do as much as possible without needing to enter the building.

How does it work?

The AFDD system typically comprises a set of rules defined by subject-matter experts (i.e., an expert system). This approach has the advantage of being expandable; however, it also has the limitation of being less flexible. The expert system becomes more complex as it is applied to different equipment and buildings.

An alternative approach is to identify and build equipment performance models based on historical data. The model continuously calculates and monitors the value of a selected performance indicator, and when it reaches the pre-defined threshold, an event (e.g., alarm, log, report) is triggered. Because the model is data-driven (and not physics-based), the model parameter values are derived from historical data that must be collected in sufficient quantity and quality.

Both approaches can be combined. The main idea remains the same – to make the important switch from being reactive to being proactive.

3. Indoor Air Quality

The pandemic has brought a new focus on the topic of indoor air quality. As we know, the SARS-CoV-2 virus mainly spreads via respiratory droplets, released when a person coughs or sneezes. The duration a virus can survive on a surface depends on multiple factors, such as surface type and environmental conditions, including air temperature and humidity. General guidance for HVAC systems includes installing high-quality filters and increasing outdoor air ventilation. It is important to find the right balance between desired environmental comfort (i.e., temperature and humidity levels) and strategies to mitigate the spread of the virus in the office space.

You need to understand how your HVAC system is performing if you want to proactively manage, not just monitor, IAQ. For example, it is important to detect early that the office room is not receiving the required ventilation levels and to analyze the root cause. This information is provided by the AFDD system in place.

IAQ improvement is an ongoing research topic because building owners need tools to regain confidence in returning to the workplace safely.

Conclusions

As presented, applying advanced analytics and machine learning in Building Analytics software clearly benefits building owners, with a high return on investment and increased tenant satisfaction. Proper software design is required to ensure the solution's scalability. Domain expertise plays an important role in algorithm selection, and the quality and quantity of collected data are essential during model design and validation.

The only remaining question is: Are you ready for the transition from reactive maintenance to proactive maintenance? We are ready to help.