LIGHTING OPTIMISATION CONTROL OF FLUO/LED SYSTEMS USING NEURAL NETWORK AND MATHEMATICAL MODEL

This article proposes a comparison of different approaches in the lighting optimization process. Beginning with the dual Fluo/LED luminaires, a neural network model is designed to represent the relationship between dimming levels of luminaires and illumination. A similar model is built with a mathematical approach and the obtained results from all these models are compared with DIALux simulation. The proposed models, implemented in a specific room, show significant energy savings according to users preference illumination. The error generated by the models is low compared to the experimental one. The proposed approach is easy to implement in a microcontroller system and is applicable in all interior building.