Building Energy Management - Heating Efficiency with No Comfort Loss
Problem
- Meeting the peak electricity and heat demand is costly and requires fossil-based, carbon-emitting fuels to be used
- Current heating optimization methods are not successful in keeping the heat at the comfort level and result in client dissatisfaction
Action
- Time-series forecasting models were used to predict room, hall and aisle temperature for various temperature set point scenarios considering weather forecast
- Data-driven heuristics algorithms were used to approximate the optimal temperature set point dynamically at every 5 minutes to keep the temperature at the desired level while reducing peak energy demand and cost of heating
Tool Stack
- AWS, Post-gre, Python
20
%Peak Demand Shaving (aka Cost Reduction)
40
%Increased Comfort
35
%Reduced CO2 Emission