Real-time daylight modeling method for lighting systems based on RBFNN

Wa Si, Xun Pan, Harutoshi Ogai

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Daylight harvesting has great potential of energy saving by utilizing daylight in buildings, and the accuracy of daylight data is essential to realize daylight harvesting in lighting control systems. This paper proposes a modified RBFNN structure for daylight modeling and presents a Real-time Daylight Modeling (RTDM) method, which needs only a few illumination sensors for real-time modeling of daylight. The method uses real-time sensor data to regulate a pre-stored RBFNN (which represents the relationship between position and daylight illuminance in one scenario of daylight) to calculate real-time daylight illuminance inside the room. Simulations in a middle-sized office model show that: 1) RTDM can realize real-time daylight modeling with higher accuracy compared with existing modeling methods; 2) lighting control system using RTDM can save considerable energy by daylight harvesting.

Original languageEnglish
Title of host publicationProceedings of 2017 9th International Conference on Computer and Automation Engineering, ICCAE 2017
PublisherAssociation for Computing Machinery
Pages318-325
Number of pages8
ISBN (Electronic)9781450348096
DOIs
Publication statusPublished - 2017 Feb 18
Externally publishedYes
Event9th International Conference on Computer and Automation Engineering, ICCAE 2017 - Sydney, Australia
Duration: 2017 Feb 182017 Feb 21

Publication series

NameACM International Conference Proceeding Series
VolumePart F127852

Other

Other9th International Conference on Computer and Automation Engineering, ICCAE 2017
Country/TerritoryAustralia
CitySydney
Period17/2/1817/2/21

Keywords

  • Daylight modeling
  • Lighting control
  • RBFNN

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Real-time daylight modeling method for lighting systems based on RBFNN'. Together they form a unique fingerprint.

Cite this