| Title |
Development of Hybrid Computational Models for Intelligent Building Systems Control |
| Keywords |
Simulation ; Neural Networks ; Hybrid Prediction Model ; Visual Performance Indicator ; Web-based Interface |
| Abstract |
This paper intends to demonstrate that analytical approaches (i.e. simulation) and inductive learning methods (i.e. neural networks) can cooperate to facilitate a daylight responsive lighting control strategy. Multiple hybrid controllers are designed to meet four control goals: enriching the informational repertoire of systems control operations for lighting (by inclusion of performance indicators for glare and solar gain), reducing the number of sensing units necessary for capturing the states of building's visual performance indicators in real time, enhancing the accuracy of predictions necessary for the identification of the best control option, and maximizing the searches in the lighting system control state space within a limited time. HISSTO (Hybrid Intelligence for System State Transition Operation), the resulting pilot control system, turned out to be capable of regulating target lighting systems effectively through a web-based interface. |