An adaptive predictive framework to online prediction of interior daylight illuminance

Sheryl G. Colaco, Anitha M. Colaco, Ciji P. Kurian, V. I. George

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

2 Citations (Scopus)

Abstract

Aiming to solve an open problem of designing a appropriate daylighting controllers, there has been growing interest in the use of nonlinear technique to perform prediction of interior daylight illuminance. Interior illuminance modeling and prediction approach provides an objective way to predict the future value of interior daylight illuminance from time series model. The urge to consider adaptive predictive technique lies in the fact that daylight is highly dynamic and nonlinear in nature. This manuscript elucidates and evaluates the performance of three nonlinear models: Nonlinear Autoregressive (NLARX), Time Delay Neural Network (TDNN) and Adaptive Neuro Fuzzy Inference Scheme (ANFIS) for accurate real time series prediction of interior daylight illuminance from online exterior and interior sensor measurements. By adopting an online tuning of model parameters by an online RLS adaptation algorithm, error between the actual system dynamics and identified model is scaled down. The exterior and interior illuminance data set for modeling are experimentally acquired from respective illuminance sensors mounted outside and inside the test chamber at Manipal (13°13'N, 77°41'E). NLARX, TDNN and ANFIS model prediction results have been validated with the real time experimental measurements. In essence, performance index comparisons of three models indicate ANFIS as a lucrative tool for the online prediction of the dynamic interior illuminance. A practical aspect of proposed ANFIS computational prediction model elevates an opportunity to couple within computer/embedded system based algorithms to perform as a real time artificial light controllers.

Original languageEnglish
Title of host publicationProceedings of the 2014 International Conference on Advances in Energy Conversion Technologies - Intelligent Energy Management
Subtitle of host publicationTechnologies and Challenges, ICAECT 2014
PublisherIEEE Computer Society
Pages174-180
Number of pages7
DOIs
Publication statusPublished - 2014
Event2014 International Conference on Advances in Energy Conversion Technologies - Intelligent Energy Management: Technologies and Challenges, ICAECT 2014 - Manipal, India
Duration: 23-01-201425-01-2014

Conference

Conference2014 International Conference on Advances in Energy Conversion Technologies - Intelligent Energy Management: Technologies and Challenges, ICAECT 2014
CountryIndia
CityManipal
Period23-01-1425-01-14

Fingerprint

Fuzzy inference
Time series
Time delay
Neural networks
Daylighting
Controllers
Sensors
Embedded systems
Dynamical systems
Tuning

All Science Journal Classification (ASJC) codes

  • Energy Engineering and Power Technology
  • Fuel Technology

Cite this

Colaco, S. G., Colaco, A. M., Kurian, C. P., & George, V. I. (2014). An adaptive predictive framework to online prediction of interior daylight illuminance. In Proceedings of the 2014 International Conference on Advances in Energy Conversion Technologies - Intelligent Energy Management: Technologies and Challenges, ICAECT 2014 (pp. 174-180). [6757083] IEEE Computer Society. https://doi.org/10.1109/ICAECT.2014.6757083
Colaco, Sheryl G. ; Colaco, Anitha M. ; Kurian, Ciji P. ; George, V. I. / An adaptive predictive framework to online prediction of interior daylight illuminance. Proceedings of the 2014 International Conference on Advances in Energy Conversion Technologies - Intelligent Energy Management: Technologies and Challenges, ICAECT 2014. IEEE Computer Society, 2014. pp. 174-180
@inproceedings{0a065b6a4e994a2584ed0ce7ceca793e,
title = "An adaptive predictive framework to online prediction of interior daylight illuminance",
abstract = "Aiming to solve an open problem of designing a appropriate daylighting controllers, there has been growing interest in the use of nonlinear technique to perform prediction of interior daylight illuminance. Interior illuminance modeling and prediction approach provides an objective way to predict the future value of interior daylight illuminance from time series model. The urge to consider adaptive predictive technique lies in the fact that daylight is highly dynamic and nonlinear in nature. This manuscript elucidates and evaluates the performance of three nonlinear models: Nonlinear Autoregressive (NLARX), Time Delay Neural Network (TDNN) and Adaptive Neuro Fuzzy Inference Scheme (ANFIS) for accurate real time series prediction of interior daylight illuminance from online exterior and interior sensor measurements. By adopting an online tuning of model parameters by an online RLS adaptation algorithm, error between the actual system dynamics and identified model is scaled down. The exterior and interior illuminance data set for modeling are experimentally acquired from respective illuminance sensors mounted outside and inside the test chamber at Manipal (13°13'N, 77°41'E). NLARX, TDNN and ANFIS model prediction results have been validated with the real time experimental measurements. In essence, performance index comparisons of three models indicate ANFIS as a lucrative tool for the online prediction of the dynamic interior illuminance. A practical aspect of proposed ANFIS computational prediction model elevates an opportunity to couple within computer/embedded system based algorithms to perform as a real time artificial light controllers.",
author = "Colaco, {Sheryl G.} and Colaco, {Anitha M.} and Kurian, {Ciji P.} and George, {V. I.}",
year = "2014",
doi = "10.1109/ICAECT.2014.6757083",
language = "English",
pages = "174--180",
booktitle = "Proceedings of the 2014 International Conference on Advances in Energy Conversion Technologies - Intelligent Energy Management",
publisher = "IEEE Computer Society",
address = "United States",

}

Colaco, SG, Colaco, AM, Kurian, CP & George, VI 2014, An adaptive predictive framework to online prediction of interior daylight illuminance. in Proceedings of the 2014 International Conference on Advances in Energy Conversion Technologies - Intelligent Energy Management: Technologies and Challenges, ICAECT 2014., 6757083, IEEE Computer Society, pp. 174-180, 2014 International Conference on Advances in Energy Conversion Technologies - Intelligent Energy Management: Technologies and Challenges, ICAECT 2014, Manipal, India, 23-01-14. https://doi.org/10.1109/ICAECT.2014.6757083

An adaptive predictive framework to online prediction of interior daylight illuminance. / Colaco, Sheryl G.; Colaco, Anitha M.; Kurian, Ciji P.; George, V. I.

Proceedings of the 2014 International Conference on Advances in Energy Conversion Technologies - Intelligent Energy Management: Technologies and Challenges, ICAECT 2014. IEEE Computer Society, 2014. p. 174-180 6757083.

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

TY - GEN

T1 - An adaptive predictive framework to online prediction of interior daylight illuminance

AU - Colaco, Sheryl G.

AU - Colaco, Anitha M.

AU - Kurian, Ciji P.

AU - George, V. I.

PY - 2014

Y1 - 2014

N2 - Aiming to solve an open problem of designing a appropriate daylighting controllers, there has been growing interest in the use of nonlinear technique to perform prediction of interior daylight illuminance. Interior illuminance modeling and prediction approach provides an objective way to predict the future value of interior daylight illuminance from time series model. The urge to consider adaptive predictive technique lies in the fact that daylight is highly dynamic and nonlinear in nature. This manuscript elucidates and evaluates the performance of three nonlinear models: Nonlinear Autoregressive (NLARX), Time Delay Neural Network (TDNN) and Adaptive Neuro Fuzzy Inference Scheme (ANFIS) for accurate real time series prediction of interior daylight illuminance from online exterior and interior sensor measurements. By adopting an online tuning of model parameters by an online RLS adaptation algorithm, error between the actual system dynamics and identified model is scaled down. The exterior and interior illuminance data set for modeling are experimentally acquired from respective illuminance sensors mounted outside and inside the test chamber at Manipal (13°13'N, 77°41'E). NLARX, TDNN and ANFIS model prediction results have been validated with the real time experimental measurements. In essence, performance index comparisons of three models indicate ANFIS as a lucrative tool for the online prediction of the dynamic interior illuminance. A practical aspect of proposed ANFIS computational prediction model elevates an opportunity to couple within computer/embedded system based algorithms to perform as a real time artificial light controllers.

AB - Aiming to solve an open problem of designing a appropriate daylighting controllers, there has been growing interest in the use of nonlinear technique to perform prediction of interior daylight illuminance. Interior illuminance modeling and prediction approach provides an objective way to predict the future value of interior daylight illuminance from time series model. The urge to consider adaptive predictive technique lies in the fact that daylight is highly dynamic and nonlinear in nature. This manuscript elucidates and evaluates the performance of three nonlinear models: Nonlinear Autoregressive (NLARX), Time Delay Neural Network (TDNN) and Adaptive Neuro Fuzzy Inference Scheme (ANFIS) for accurate real time series prediction of interior daylight illuminance from online exterior and interior sensor measurements. By adopting an online tuning of model parameters by an online RLS adaptation algorithm, error between the actual system dynamics and identified model is scaled down. The exterior and interior illuminance data set for modeling are experimentally acquired from respective illuminance sensors mounted outside and inside the test chamber at Manipal (13°13'N, 77°41'E). NLARX, TDNN and ANFIS model prediction results have been validated with the real time experimental measurements. In essence, performance index comparisons of three models indicate ANFIS as a lucrative tool for the online prediction of the dynamic interior illuminance. A practical aspect of proposed ANFIS computational prediction model elevates an opportunity to couple within computer/embedded system based algorithms to perform as a real time artificial light controllers.

UR - http://www.scopus.com/inward/record.url?scp=84897477395&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897477395&partnerID=8YFLogxK

U2 - 10.1109/ICAECT.2014.6757083

DO - 10.1109/ICAECT.2014.6757083

M3 - Conference contribution

AN - SCOPUS:84897477395

SP - 174

EP - 180

BT - Proceedings of the 2014 International Conference on Advances in Energy Conversion Technologies - Intelligent Energy Management

PB - IEEE Computer Society

ER -

Colaco SG, Colaco AM, Kurian CP, George VI. An adaptive predictive framework to online prediction of interior daylight illuminance. In Proceedings of the 2014 International Conference on Advances in Energy Conversion Technologies - Intelligent Energy Management: Technologies and Challenges, ICAECT 2014. IEEE Computer Society. 2014. p. 174-180. 6757083 https://doi.org/10.1109/ICAECT.2014.6757083