AustraliaReal estate2022 – ongoingVicinity Centres
Machine-learning forecasts for shopping-centre energy demand
Vicinity Centres used 24-hour energy forecasts to reduce peak consumption
Problem
Peak electricity consumption influenced the tariffs paid by Vicinity's shopping centres. Operations teams needed advance warning of demand to manage those peaks.
Approach
Vicinity's internal data science team built a machine-learning model to forecast energy demand. It used footfall and weather alongside calendar and time information. Centre operations teams used the forecasts to adjust consumption.
Results
Takeaway
The forecasts supported operating decisions at individual centres. Tableau reported cost avoidance without disclosing a monetary amount or a measured reduction in peak demand.
Categories
- Industry
- Real estate
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Built in-house
- Goal
- Cost savings
- Evidence
- Vendor case study
Sources
Source summaries
Tableau described Vicinity's internal machine-learning model for forecasting electricity demand 24 hours ahead. It reported that operations teams used the forecasts to reduce peak consumption and avoid costs, without quantifying the savings.
Full details are in the original sources.
