With the push to implement sustainability in companies and organizations, energy savings is a significant initiative for facilities managers and owners. By using smart building solutions and automation to control and monitor energy consumption, they can manage lighting, HVAC parameters and more.

However, using business analytics to capture information through “big data” about energy consumption shows promise. This would provide fact-based information about energy consumption patterns at very granular levels so facilities and building managers can be more proactive in their management.

At Incheon National University in Korea, a research team led by professor Choongwan Koo developed a model that uses large volumes of data to, as he calls it, “meet the challenges of accurate occupant-level measurements, including variations in space, time and appliances/equipment.”

His study, “A novel process model for developing a scalable room-level energy benchmark using real-time bigdata: Focused on identifying representative energy usage patterns,” states in its abstract that this proposed business model “may be appropriate for formulating community-level energy strategy at the macro level, but it cannot be directly linked to occupant behavior for energy savings at the micro level. In light of this, this study aimed to propose a novel process model for developing a scalable room-level energy benchmark using real-time big data, which focused on identifying representative energy usage patterns and encouraging occupant behavior change for energy savings.”

How did they go about building their model?

The research team used an educational facility in Sangju, Korea, as a sample building. Each classroom was equipped with electrical meters in all classrooms, with internet of things energy sensors that measure data in real-time. In total, they collected about 11 million datasets.

Once data was gathered, they applied analytics to extract inferences and consider energy from three angles: each space unit based on occupant perception, a time unit allowing rapid response from occupants and data from the appliance-level or equipment unit.

Then the academic researchers applied a “k-clustering algorithm” to drill into the data and identify energy clusters. This led to looking at energy consumption patterns and then nailing down energy benchmarks that could be applied and were scalable.

More specifically, they looked at lighting, educational devices, cooling, heating and many of the more low-hanging fruit of energy consumption. The team applied mathematical rules to validate their benchmarks and determine their accuracy. The data was correlated with more sophisticated parameters such as ambient weather conditions and the specific consumption patterns extracted hour by hour from the room unit level of data.

“The scalable energy benchmarks can help in the planning of effective operational strategies to boost energy savings. It also improves energy efficiency and Indoor Environmental Quality. For example, during periods of peak consumption, like summer afternoons and winter mornings, different strategies for saving energy on cooling and heating systems could be applied. Likewise, methods to turn off the standby power when the facility is not in use can be developed,” Koo said.

It almost sounds as if this is something that would have already been completed by most smart building energy managers and manufacturers. However, it seems the key difference is the magnitude of data gathered, and the granularity of that big data. Both attributes enabled them to develop benchmarks at a level that was not previously performed.

It could mark the start of something new and innovative in the quest to gather data about energy consumption and be able to act, make management decisions and bring about meaningful savings.

It’s something that electrical contractors should be interested in as more organizations are improving their approaches to energy management with smart devices to generate savings from less energy consumption and reduce their carbon footprint.