Skip to main content
Back to challenges
Challenge

Commercial Real Estate Energy & Space Optimization Pipeline

Smart commercial real estate demands active integration between occupancy sensors and HVAC energy automation. Build a dynamic space and energy optimization agent using Scikit-Learn and FastAPI to adjust building cooling based on real-time headcount predictions. Achieve reduced energy consumption while preserving environmental comfort scores.

Workflow AutomationHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Build an IoT HVAC energy optimization agent using Scikit-Learn and FastAPI for commercial office towers.

Delivery guide

How work is evaluated

Evaluation

Evaluates predicted occupancy accuracy and HVAC setpoint recommendation validity.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

comfort_bounds_check

Ensures temperature setpoint remains strictly between 20.0C and 24.0C.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

forecast_mae

Mean Absolute Error of occupancy prediction model. • target: 1.2 • range: 0-5

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Train occupancy forecasting models using Scikit-Learn regression algorithms

  • Expose real-time dynamic temperature set-point endpoints using FastAPI

  • Balance indoor air quality (CO2 levels) against chiller energy draw

  • Implement automated alert triggers for HVAC maintenance anomalies

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic commercial office space IoT dataset containing temperature, CO2, motion sensor readings, and energy draw.

Challenge setup

Evaluates predicted occupancy accuracy and HVAC setpoint recommendation validity.

Challenge input

JSON sensor snapshot

FastAPI

Standard high-performance Python web framework.

Evaluated output

JSON setpoint control signal

Evaluation checks
  • Ensures temperature setpoint remains strictly between 20.0C and 24.0C.
  • Mean Absolute Error of occupancy prediction model. • target: 1.2 • range: 0-5
Configured evaluation evidence
  • Benchmark: SmartBuilding-HVAC-Bench
  • Forecast Mae target: 1.2
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • Shakudo · Required
  • AgentFlow · Optional
  • Ray Tune · Optional

Evaluation contract

  • comfort_bounds_check · Weight 1
  • forecast_mae · Weight 1

Metrics

  • forecast_mae · Target 1.2

Benchmarks

  • SmartBuilding-HVAC-Bench
  • energy

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON sensor snapshot

    Output: JSON setpoint control signal

    Execution harness: Python

Evaluation tools

  • FastAPI · API Service Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Commercial Real Estate Energy & Space Optimization Pipeline