Publications in Scientific Journals:

S. Chang, A. Mahdavi:
"A Hybrid System for Daylight Responsive Lighting Control";
Journal of the Illuminating Engineering Society, 31 (2002), 1; 147 - 157.

English abstract:
Problem Identification

With the advances in computation and DDC (Direct Digital Control), the model-based building control becomes an attractive option. A model may not always precisely capture the actual system behavior due, in part, to the difficulty of acquiring exact descriptions of building system properties, such as materials and construction features. Some simulation programs are computationally too intensive to be effective for real-time control purpose. An example is a lighting simulator that uses ray-tracing in the modeling process. Such simulation programs cannot be used for control purposes unless the pertinent control state search space is dramatically reduced. Machine learning can address this problem; however, it often requires large amounts of data for training. Before a neutral network is trained, or if it encounters unexpected conditions, it is not able to predict accurately. The need for retraining makes it difficult for a machine learner to respond quickly to the system retrofit and/or seasonal weather pattern changes. Its sensor- dependency represents an additional difficulty, especially when placing and/or maintaining sensor that are costly or otherwise not desirable. Conventional lighting control systems do not necessarily allow multiple control modes such as manual mode, scheduled mode, and automatic mode. Limitation of access due to the location-dependency of the system control also needs to be addressed.

Electronic version of the publication:
http://www.bpi.tuwien.ac.at/publications/2002-2003/abstract_a hybride system for daylight responsive lightning control.pdf

Created from the Publication Database of the Vienna University of Technology.