Adaptive lighting control in intelligent buildings using artificial neural networks: design, implementation, and...

Area of Science:

• Building Automation
• Artificial Intelligence
• Energy Efficiency

Background:

• Intelligent lighting control systems are crucial for optimizing energy consumption in modern buildings.
• Existing systems often struggle with dynamic adjustments to daylight and occupancy.
• Adaptive control is needed to maintain desired illuminance levels efficiently.

Purpose of the Study:

• To design, implement, and validate an artificial neural network (ANN)-based intelligent lighting control system.
• To optimize energy consumption by adaptively adjusting artificial lighting based on real-time conditions.
• To demonstrate the system's effectiveness in a real-world office environment.

Main Methods:

• Development of a feedforward neural network trained offline and deployed on an embedded unit.
• Focus on embedded deployment and long-term field operation in an intelligent building.
• Experimental validation measuring energy savings and illuminance levels.

Main Results:

• Achieved consistent energy savings of 7.4-12.5% during continuous operation and 8.5% under occupancy-driven conditions.
• Maintained required illuminance levels with high predictive accuracy (R² = 0.91) and stable performance.
• Demonstrated smooth dimming transitions and reduced illuminance fluctuations compared to conventional systems.

Conclusions:

• ANN-based adaptive lighting control offers a practical, scalable, and energy-efficient solution for building automation.
• The system enables real-time operation on low-cost hardware, suitable for retrofit applications.
• Findings provide a basis for further validation across diverse building types and climates.