Overview: Driving Efficiency with Structure Workflow

This use case demonstrates how arkEMIS was used to identify and resolve an operational inefficiency in an Air Handling Unit (AHU) serving office spaces. By leveraging Ark Energy’s Detect–Measure–Analyze–Improve–Control workflow, the system enabled data-driven decision-making and measurable energy savings.
The Air Handling Unit began exhibiting abnormal energy consumption patterns over time.
The Sentinel Trend machine learning module (Detect) identified multiple instances of overconsumption, reaching approximately 28% above normal levels during April


Monthly consumption data showed a steady increase throughout the first quarter (Measure) 


Heatmap analysis revealed that the AHU was running continuously, including outside working hours and weekends, despite low to no occupancy 

This pointed to a clear operational inefficiency driven by improper scheduling.


 

Solution: Applying the Detect–Measure–Analyze–Improve–Control Approach

Using arkEMIS, the issue was addressed through a structured, data-driven workflow:

Analyze: The Operations Analyzer evaluated system behavior and confirmed that continuous operation was the main driver of excess consumption.

Improve: Scenario simulations showed that turning off the AHU outside working hours could reduce energy use by up to 50%. A low-cost / no-cost measure was recommended to the on-site team.

Results and Progress

Following implementation, the recommended scheduling adjustments were successfully adopted by the operations team, shifting the Air Handling Unit from continuous operation to occupancy-based usage. This change led to a clear stabilization in consumption patterns after a period of continuous increase during the first quarter. Through ongoing tracking, arkEMIS verified a 20% reduction in daily average energy cost, confirming the effectiveness of the measure. The platform also highlighted a broader optimization potential of up to 50% energy savings, reinforcing the value of aligning equipment operation with actual demand. Continuous monitoring ensured that these improvements were not only achieved but maintained over time.


 

Conclusion

This use case demonstrates how arkEMIS enables organizations to uncover hidden inefficiencies and act on them quickly and effectively. By combining machine learning detection with actionable analytics and continuous monitoring, significant energy savings were achieved without any capital investment.

It highlights the power of a structured workflow in turning insights into sustained operational improvements.