How Can Data Analytics Be Used To Enhance HVAC Solutions?

An issue that many HVAC system operators must deal with is managing competing priorities. For example, an operator may need to run the system at a high-efficiency level to meet sustainability targets. This means spending less energy to respond to occupant comfort requests. If it’s hot outside, the building will warm up, and occupants will demand a cooler environment. Responding to this push-and-pull can compromise system efficiency and impact a facility’s overall sustainability and decarbonization plans. Using data points, including weather reports, equipment operation statistics, and room occupancy information, the operator can apply analytics to find a happy medium that maximizes efficiencies while catering to occupants’ needs. All too often operators are caught in a tug-of-war over competing priorities. Data analytics can steer their choices to achieve a balanced HVAC solution.

Remote monitoring is one of the fastest-growing HVAC technologies, and for good reason. Remote monitoring products tie into the greater smart building, smart city ecosystem and allow private and government entities to proactively monitor HVAC condition, performance, energy efficiency, along indoor air quality. All of this data can then be utilized for a variety of activities such as identifying malfunctions in units before or right as they occur – shortening downtimes for critical facilities like hospitals, improving energy efficiency across a network of units by adjusting settings based on analyzed data, providing accurate capital expenditure estimates by taking into account unit age and condition, and many more such applications. The future of HVAC technology is very exciting both on a micro and macro scale, as technology becomes more commonly integrated with residential and commercial property management.

Data analytics can play a pivotal role in HVAC solutions. This can be achieved by taking historic data to understand actual “in use” operational loads required and comparing them against those designed. The benefit of this approach is that it may influence the design dramatically, driving both a lower CapEx and OPEX, in addition to the potential improvement in user comfort. Using data analytics also means that we can draw on this data to understand trends. This knowledge has the potential to drive more effective solutions earlier in the design stages, meaning that we all start from an informed position, rather than carrying out value engineering exercises further down the line. The impact of such an approach is that we can accelerate design, reduce potential changes, and help with an organization’s carbon goals.

By applying algorithms that process the data monitored by building automation systems, building operators can diagnose existing faults, predict when failures are likely to occur, identify equipment that is not operating at expected efficiency, and automatically “tune” the system to improve energy efficiency and minimize carbon emissions based on historical performance. A key to enabling such analytics is to implement semantic tagging of data points in the system, most simply by using the Project Haystack tagging and data model open standard. Once implemented, much can be achieved by the creation of a set of “rules” – snippets of logic created graphically, which are then applied by the use of tagging across a whole project. Examples of the types of analytics rules include detection of simultaneous heating and cooling, identification of faulty dampers or valves, exceptional energy consumption compared to the previous period(s) with comparable conditions, and avoidance of energy usage during peak periods.

Data analytics are key in enabling preventative maintenance.  BMSs (Building management systems) can monitor data from devices in the field to check plant operation. This includes hours-run information and measured values. These can be monitored, and thresholds set up which if exceeded can trigger an instruction by text or email to investigate conditions or run a planned maintenance operation. A simple example is measuring the differential pressure across a filter with a sensor. If the measured value goes outside acceptable parameters, a maintenance instruction is sent to the correct operative to carry out the necessary investigation. BMSs allow this to be sent to different people at different times due to shift patterns. There are cost and operational benefits in addressing issues before they become critical. These can only be delivered if the correct data analytics regime is set up in the BMS.