Indoor sensing and home automation

Synthetic Smart Home sensor data for IoT research

Smart Home records combine indoor thermal relaxation, humidity, carbon-dioxide mass balance, occupancy states, and HVAC behaviour into time-series data for research use.

Generate a dataset Explore original records

Engine maturity

Experimental Engine — Under Scientific Review

This domain is an early-stage research prototype. Its models, units, temporal behaviour, and event semantics are being audited. Outputs should not be treated as empirically validated observations.

engine 3.2.0 · maturity experimental · validation audit_pending

Research scope

Researchers can inspect the original generated record, its documented configuration, and its citation guidance before using the CSV in an experiment.

Indoor temperature, humidity, CO2 concentration, occupancy, and HVAC state

Scenario-specific sensor data for automation and time-series modelling

Column schema

Every record in this domain emits the same 8 columns . Types and ranges below are read from the generator itself, so they cannot drift from the files it produces.

Column Type Range
Timestamp datetime —
Room categorical —
Temp_C float 15, 35
Humidity_Pct float 25, 85
CO2_ppm integer 380, 2500
Light_Lux integer 0, 1000
Occupancy integer 0, 8
HVAC_Status categorical —

Generative models

Values come from explicit equations, not from a trained generative model. Each component below is documented in the methodology.

Indoor temperature

ISO 13790

T(t+dt) = T_target + (T(t) - T_target) exp(-dt/tau) + AR(1) noise - RC thermal relaxation toward the HVAC target.

Outdoor driver

Multi-harmonic Fourier temperature driver.

Humidity

Psychrometric conversion via Magnus-Tetens.

Carbon dioxide

Analytic solution of dC/dt = (n.G - Q(C - C_out))/V.

Occupancy

Markov occupancy chain.

HVAC

Deadband thermostat control.

Research uses

The common thread is known ground truth: the generator records the true state alongside the observation of it, which a real deployment cannot supply.

Occupancy inference from indirect sensors where true occupancy is known

HVAC control-policy evaluation

Anomaly detection with labelled injected anomalies

Teaching time-series modelling on physically consistent data

Compared with measured datasets

Measured datasets in this area remain the reference for site realism. A generator answers a different question: what a method does when the true state is known and the scenario can be set deliberately. These are complements, not substitutes.

Measured dataset What it provides What a generated record adds
CASAS Instrumented smart-home testbeds with activity annotation. Exact occupancy ground truth rather than post-hoc human annotation.
UCI Occupancy Detection Office-room temperature, humidity, light and CO2 with occupancy labels. Controllable room count, schedule and sensor error.
REFIT Household electrical load monitoring. Physically coupled thermal, humidity and CO2 dynamics alongside occupancy.

Scope and limits

What is currently established

  • — The generator runs and emits its declared column contract.
  • — Output is deterministic for a given domain, parameter set and seed.
  • — Scientific audit of its models, units, temporal behaviour and event semantics is still outstanding.

What it does not establish

  • — Site realism, or transfer to any specific real deployment.
  • — Calibration against a named site, sensor network, fleet or population.

Read the full research record →

Browse Smart Home generated records

Each card links to the original citable record. IoTSyn keeps that URL, its dataset file, and its citation guidance unchanged.

Open the full library

Frequently asked questions

Does this replace a real smart-home deployment?

No. It supplies known ground truth for benchmarking, such as the true occupancy behind a noisy sensor, which a real deployment cannot provide.

Are the thermal dynamics physically grounded?

Yes. Indoor temperature uses RC thermal relaxation toward the HVAC target following ISO 13790, with Magnus-Tetens psychrometric humidity and an analytic carbon-dioxide mass balance.

Can room count and occupancy be controlled?

Yes. Scenario parameters are declared per record and published alongside it.

Is the data suitable for training occupancy classifiers?

Yes, with the caveat that it is not calibrated to a specific dwelling. It is designed for method development and controlled benchmarking rather than site-specific deployment.

Explore other synthetic-data topics

Synthetic Smart City datasets for urban IoT research

Open topic page →

Synthetic predictive maintenance datasets for condition monitoring

Open topic page →

Synthetic Medical IoT datasets for health-data research

Open topic page →

Synthetic IIoT network traffic datasets for security research

Open topic page →

Synthetic connected-vehicle telemetry datasets

Open topic page →