PLEIAData: consumption, HVAC, temperature, weather and motion sensor data for smart buildings applications

Area of Science:

• Building energy efficiency
• Artificial Intelligence in energy management
• Internet of Things (IoT) applications

Background:

• High energy consumption in climate control necessitates cost reduction strategies.
• The proliferation of Information and Communication Technology (ICT) and IoT enables advanced energy management.
• Building performance data is key to developing effective energy-saving control strategies.

Purpose of the Study:

• To introduce a novel dataset for AI-driven energy consumption and temperature modeling.
• To support the development of intelligent control systems for buildings.
• To facilitate research in optimizing energy efficiency and occupant comfort.

Main Methods:

• Data collection over one year in a pilot building (Pleiades) at the University of Murcia.
• Utilizing sensor data on internal and external building conditions.
• Dataset designed for Artificial Intelligence (AI) algorithms for predictive modeling.

Main Results:

• A comprehensive dataset capturing building environmental parameters and energy usage.
• The dataset provides features crucial for AI model training in energy management.
• Enables analysis for minimizing energy consumption while ensuring user comfort.

Conclusions:

• The presented dataset is valuable for AI applications in building energy optimization.
• Facilitates the advancement of smart building technologies for improved energy efficiency.
• Supports the goals of projects like PHOENIX in enhancing building energy performance.