FlexTrack: Detecting Energy Flexibility in Buildings
It’s Monday afternoon in a busy office building. The air conditioning ramps up, lights flick on in meeting rooms, and laptops charge at every desk. Energy use naturally rises and falls throughout the day, but sometimes the grid calls for a change: reduce power for the next hour, or even draw more to stabilise supply. The building adapts as thermostats shift, non-essential equipment pauses, and batteries discharge.
From the outside, nothing looks different, but behind the scenes, energy use has flexed by reducing, shifting, or even increasing load to support the grid. To trade in this flexibility market, energy providers need a reliable way to detect not just when demand response happens but also how much energy was actually flexed.
Enter FlexTrack Challenge
This challenge calls on participants to build machine learning models that can identify demand response events and measure their impact by distinguishing normal energy use from intentional shifts.
HVAC systems, batteries, and solar inverters can all provide flexibility. To trade in energy flexibility markets, energy providers must detect when a demand response occurred and measure how much load was shifted or shed.
The Task
Participants will use time-series datasets from commercial office building digital twins across three Australian climate zones to:
Task 1 – Classification
Predict the demand response flag at 15-minute intervals:
• -1 for decreased load
• +1 for increased load
• 0 for baseline consumption
Task 2 – Regression
Estimate the demand response capacity in kilowatts during an event compared to the baseline.
Both tasks require models that are accurate, scalable, and transferable to different sites.
Dataset
• Data includes dry bulb temperature, global horizontal radiation, building power, demand response flag, and demand response capacity.
• Synthetic data generated from validated digital twins at the University of Wollongong.
• 15-minute resolution, covering multiple climate zones.
Timeline
• Website & Registration: 18 Aug 2025
• Data Release: 19 Aug 2025
• Phase 1 Start: 19 Aug 2025, 23:59 UTC
• Phase 2 Start: 15 Sep 2025, 23:59 UTC
• Documentation Deadline: 19 Oct 2025, 23:59 UTC
Prizes
Total prize pool: $20,000 AUD plus travel grants to present at the 2025 IEEE International Conference on Energy Technologies for Future Grids.
Leaderboard Prizes
1st Place – $5,000 AUD
2nd Place – $3,000 AUD
2 × $1,000 AUD
Travel Grants
Awarded to all four winners for in-person presentations.
Get Involved
FlexTrack is your opportunity to shape the future of smart energy systems. Build solutions that detect flexibility accurately and help buildings play an active role in a stable, low-carbon grid.