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

Wa Si, Xun Pan, Harutoshi Ogai

研究成果: Conference contribution

抄録

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.

本文言語English
ホスト出版物のタイトルProceedings of 2017 9th International Conference on Computer and Automation Engineering, ICCAE 2017
出版社Association for Computing Machinery
ページ318-325
ページ数8
Part F127852
ISBN(電子版)9781450348096
DOI
出版ステータスPublished - 2017 2 18
イベント9th International Conference on Computer and Automation Engineering, ICCAE 2017 - Sydney, Australia
継続期間: 2017 2 182017 2 21

Other

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

ASJC Scopus subject areas

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

フィンガープリント 「Real-time daylight modeling method for lighting systems based on RBFNN」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル