TY - GEN
T1 - A novel energy saving system for office lighting control by using RBFNN and PSO
AU - Si, Wa
AU - Ogai, Harutoshi
AU - Li, Tansheng
AU - Hirai, Katsumi
PY - 2013/9/16
Y1 - 2013/9/16
N2 - This paper represents a novel energy saving system for office lighting control which consists of LED lamps, one illumination sensor for measuring the natural illumination condition, and one control module for the integrated control. The control module embeds an intelligent algorithm for generating the optimized dimming pattern according to the natural illumination and occupancy condition. The intelligent algorithm contains 1) Radial Basis Function Neural Networks (RBFNN) which are used to calculate the illuminance contribution from each luminaire to different positions in the office 2) a PSO algorithm which is used to optimize dimming ratio for luminaires according to the target illuminance in occupied areas thus provide optimized control strategy for the office. Simulations are made to prove the feasibility and effectiveness of the illumination simulator.
AB - This paper represents a novel energy saving system for office lighting control which consists of LED lamps, one illumination sensor for measuring the natural illumination condition, and one control module for the integrated control. The control module embeds an intelligent algorithm for generating the optimized dimming pattern according to the natural illumination and occupancy condition. The intelligent algorithm contains 1) Radial Basis Function Neural Networks (RBFNN) which are used to calculate the illuminance contribution from each luminaire to different positions in the office 2) a PSO algorithm which is used to optimize dimming ratio for luminaires according to the target illuminance in occupied areas thus provide optimized control strategy for the office. Simulations are made to prove the feasibility and effectiveness of the illumination simulator.
KW - Energy Saving System
KW - Office Lighting
KW - Particle Swarm Optimization
KW - Radial Basis Function Neural Networks
UR - http://www.scopus.com/inward/record.url?scp=84883664708&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84883664708&partnerID=8YFLogxK
U2 - 10.1109/TENCONSpring.2013.6584469
DO - 10.1109/TENCONSpring.2013.6584469
M3 - Conference contribution
AN - SCOPUS:84883664708
SN - 9781467363495
T3 - IEEE 2013 Tencon - Spring, TENCONSpring 2013 - Conference Proceedings
SP - 347
EP - 351
BT - IEEE 2013 Tencon - Spring, TENCONSpring 2013 - Conference Proceedings
T2 - 2013 1st IEEE TENCON Spring Conference, TENCONSpring 2013
Y2 - 17 April 2013 through 19 April 2013
ER -