The Development of an Energy Efficient Temperature Controller for Residential Use and Its Generalization Based on...

Area of Science:

• Building energy systems
• Thermal analysis
• Artificial intelligence in HVAC

Background:

• Intelligent home automation and thermostats are crucial for occupant comfort and energy efficiency.
• Control strategies must adapt to environmental changes like wind and fluctuating temperatures.
• Accurate heat transfer estimation is vital for effective building climate control.

Purpose of the Study:

• To propose a new approach for estimating residential building heat transfer.
• To develop and test advanced control strategies for HVAC systems.
• To improve the energy efficiency and responsiveness of smart thermostats.

Main Methods:

• Utilized a lumped parameter thermal analysis model for heat transfer estimation.
• Implemented and tuned various control strategies in a virtual environment.
• Employed a long short-term memory (LSTM) neural network to generalize control knowledge.
• Validated the approach through laboratory-scale experiments.

Main Results:

• The proposed model accurately estimates building heat transfer.
• The generalized LSTM model effectively adapts control strategies.
• The implemented temperature controller demonstrated reduced overshoot.
• Significant improvements in energy consumption were observed.

Conclusions:

• The novel approach enhances the performance of smart thermostats.
• The integration of lumped parameter models and LSTM networks offers a robust solution for HVAC control.
• The developed controller effectively balances comfort and energy efficiency in residential buildings.