Objective: Reduce costs associated to HVAC systems, while ensuring occupants comfort by predicting the energy demand and consumption.
Description: ML model predicts optimal HVAC settings based on occupancy patterns, weather forecasts, and thermal behavior of the building, taking into account the calculated costs, and the temperature inside the building
Data Required:
- Historical HVAC energy consumption
- Occupancy patterns
- Weather data (external temperature, humidity, solar radiation)
- Building metadata (thermal characteristics of the building (W/m²·K), area of the floors, number of floors, etc..)
How we solve it:
Delivered results:
- Real-time monitoring of any of the variables of the dataflow, like the temperature of the building and its calculated Carbon footprint.
- Historical plot with building utilization vs energy consumption
- Recommendations for the HVAC setpoint in order to reduce costs while ensuring comfort
- Alarms configured with specific logic customized for the building scheduling