A Novel Lambertian-RBFNN for Office Light Modeling

Abstract

SUMMARYIn lighting control systems, accurate data of artificial light (lighting coefficients) are essential for the illumination control accuracy and energy saving efficiency. This research proposes a novel LambertianRadial Basis Function Neural Network (L-RBFNN) to realize modeling of both lighting coefficients and the illumination environment for an office. By adding a Lambertian neuron to represent the rough theoretical illuminance distribution of the lamp and modifying RBF neurons to regulate the distribution shape, L-RBFNN successfully solves the instability problem of conventional RBFNN and achieves higher modeling accuracy. Simulations of both single-light modeling and multiple-light modeling are made and compared with other methods such as Lambertian function, cubic spline interpolation and conventional RBFNN. The results prove that: 1) L-RBFNN is a successful modeling method for artificial light with imperceptible modeling error; 2) Compared with other existing methods, L-RBFNN can provide better performance with lower modeling error; 3) The number of training sensors can be reduced to be the same with the number of lamps, thus making the modeling method easier to apply in real-world lighting systems.

Modeling occupant behavior in buildings

“…The most frequent category is the data-driven models [121,144,[161][162][163][164][165][166][167][168][169][170]148,[171][172][173][174][175][176][177][178][179][180]149,[181][182][183][184][185][186][187][188][189][190]152,[191][192][193][194][155][156][157][158]160], followed by the stochastic OPA modeling methods [153,159,[195][196][197][198][199]…”

“…As a prediction method, linear regression is easy to use, and the historical use rate is similar to SVMs and decision trees. Researchers validated their models by means of different evaluation metrics: error or accuracy [149,155,[202][203][204]164,166,170,177,179,180,186,201]; comparison between the performances of the proposed system and the existing system in terms of energy saving or illumination level [139,153,221,173,174,181,191,192,194,199,206];…”