Intelligent Indoor Environment Dataset for Smart Home Energy Optimization

Dataset Overview

This comprehensive dataset is designed for optimizing energy consumption and enhancing occupant comfort in smart indoor environments. It includes real-time environmental data collected from IoT devices deployed in smart homes, capturing critical variables such as room conditions, occupant behaviors, and automated system controls over extended monitoring periods.

Key Features

• 15-minute interval data collection for granular time-series analysis
• Multi-sensor environmental monitoring (temperature, humidity, lighting, air quality)
• CO2 level tracking for indoor air quality assessment
• Occupancy detection and prediction capabilities
• HVAC and lighting control system data
• Energy consumption metrics with associated costs
• Occupant behavior patterns including entry/exit predictions
• CSV format for easy integration with ML frameworks

Data Structure

The dataset contains the following features organized in structured CSV format:

• Timestamp: Date and time of measurement (15-minute intervals)
• Room Temperature: Ambient temperature in Celsius
• Room Humidity: Relative humidity percentage
• Lighting Intensity: Light level measurement in lux
• Room Air Quality: Air quality index representing overall conditions
• CO2 Levels: Carbon dioxide concentration in ppm
• Occupancy Status: Binary indicator of room occupancy
• Predicted Entry/Exit Times: Behavioral prediction features
• HVAC Temperature Setting: Thermostat control values
• Lighting Control: Automated lighting system states
• Energy Consumption: Power usage in kWh
• Energy Cost: Associated electricity costs

Data Collection Method

Data was collected from IoT sensor networks deployed in real smart home environments. The system utilizes distributed sensors for environmental monitoring, occupancy detection through motion and door sensors, and smart meters for energy consumption tracking. All measurements are synchronized and logged at 15-minute intervals to capture daily patterns while maintaining manageable data volumes.

Research Applications

• Energy consumption forecasting and optimization algorithms
• Occupancy prediction for demand-responsive systems
• Indoor air quality monitoring and control strategies
• HVAC optimization for energy efficiency and comfort balance
• Behavioral pattern analysis for personalized automation
• Smart home system evaluation and benchmarking
• Cost-effective energy management solutions
• Thermal comfort modeling and prediction

Machine Learning Use Cases

• Time series forecasting for energy consumption and occupancy
• Regression models for temperature and HVAC optimization
• Classification for occupancy detection and activity recognition
• Reinforcement learning for adaptive HVAC control
• Clustering analysis for behavioral pattern discovery
• Anomaly detection for system faults and unusual consumption
• Multi-variate prediction combining environmental and behavioral data
• Deep learning (LSTM, GRU) for temporal pattern recognition
• Transfer learning for different home configurations