Autonomous Lighting Control Based on Adjustable Illumination Model

Autonomous lighting control systems require a numerical illumination model in which the light level output in a room can be expected according to given dimming control inputs. Stationary illumination models, such as the zonal cavity method and the point by point method, might be difficult to adjust the model to on-site environments in which are suffused with various shading artifacts unconsidered in a preceding simulation stage. Thus, this paper suggests an adjustable illumination model through Neural Network which can fit the model to the environments by a learning technology. Secondly, the autonomous lighting control can be realized by using the inverse of the illumination model. A small-sized replica of an actual lighting space is used for evaluation of our approach.