Neural computing thermal comfort index for HVAC systems

Atthajariyakul, Surat; Leephakpreeda, Thananchai

doi:10.1016/j.enconman.2004.12.007

Cited by 110 publications

(65 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this work it is shown that by following a simpler and more appropriate approach, it is possible to select a desired compromise between accuracy and execution time. More importantly it is shown that, when compared to the results in [29][30][31], an increased accuracy with shorter execution time may be achieved.…”

Section: Predicted Mean Votementioning

confidence: 97%

See 1 more Smart Citation

Neural networks based predictive control for thermal comfort and energy savings in public buildings

Ferreira¹,

Ruano²,

Silva³

et al. 2012

Energy and Buildings

381

219

View full text Add to dashboard Cite

a b s t r a c tThe paper addresses the problem of controlling a Heating Ventilation and Air Conditioning (HVAC) system with the purpose of achieving a desired thermal comfort level and energy savings. The formulation uses the thermal comfort, assessed using the predicted mean vote (PMV) index, as a restriction and minimises the energy spent to comply with it. This results in the maintenance of thermal comfort and on the minimisation of energy, which in most conditions are conflicting goals requiring an optimisation method to find appropriate solutions over time. A discrete model-based predictive control methodology is applied, consisting of three major components: the predictive models, implemented by radial basis function neural networks identified by means of a multi-objective genetic algorithm; the cost function that will be optimised to minimise energy consumption and maintain thermal comfort; and the optimisation method, a discrete branch and bound approach. Each component will be described, with special emphasis on a fast and accurate computation of the PMV indices. Experimental results obtained within different rooms in a building of the University of Algarve will be presented, both in summer and winter conditions, demonstrating the feasibility and performance of the approach. Energy savings resulting from the application of the method are estimated to be greater than 50%.

show abstract

Section: Predicted Mean Votementioning

confidence: 97%

“…The application of an ANN to estimate the PMV index function has been studied before [29][30][31]. In all cases the approach taken was not the best for real-time control applications although this was the main motivation.…”

Section: Predicted Mean Votementioning

confidence: 99%

Neural networks based predictive control for thermal comfort and energy savings in public buildings

Ferreira¹,

Ruano²,

Silva³

et al. 2012

Energy and Buildings

381

219

View full text Add to dashboard Cite

show abstract

“…The percentage signed error (PSE) is the percentage of predictions with the same sign as the observed value. 16 The results show that the GP models predict the correct direction ∼65% of the time while the PMV is correct ∼50% of the time which is equivalent to a random guess. 17 Between the GP models there is no clear winner.…”

Section: Group Resultsmentioning

confidence: 75%

“…1 In addition, a recent study has proposed that the PMV is now a biased estimate of the average users preference in many regions of the world [13]. Further approaches seek to dynamically adjust the setpoint using measured environment variables but all without a human feedback mechanism [14][15][16]. One recent notable approach uses Bayesian probit analysis to map PMV and environmental measures to sensation, acceptability and preference [17] providing a deeper understanding of human perception of their environment.…”

Section: Related Workmentioning

confidence: 99%

Gaussian Process models for ubiquitous user comfort preference sampling; global priors, active sampling and outlier rejection

Fay

O'Toole

Brown

2017

Pervasive and Mobile Computing

View full text Add to dashboard Cite

a b s t r a c tThis paper presents a ubiquitous thermal comfort preference learning study in a noisy environment. We introduce Gaussian Process models into this field and show they are ideal, allowing rejection of outliers, deadband samples, and produce excellent estimates of a users preference function. In addition, informative combinations of users preferences becomes possible, some of which demonstrate well defined maxima ideal for control signals. Interestingly, while those users studied have differing preferences, their hyperparameters are concentrated allowing priors for new users. In addition, we present an active learning algorithm which estimates when to poll users to maximise the information returned.

show abstract

“…The literature reveals a wide use of ANN for the control and management of building environments [19][20].…”

Section: Artificial Neural Network For Building Energy Managementmentioning

confidence: 99%

ANN–GA smart appliance scheduling for optimised energy management in the domestic sector

Yüce

Rezgui

Mourshed

2016

Energy and Buildings

125

View full text Add to dashboard Cite

Neural computing thermal comfort index for HVAC systems

Cited by 110 publications

References 14 publications

Neural networks based predictive control for thermal comfort and energy savings in public buildings

Neural networks based predictive control for thermal comfort and energy savings in public buildings

Gaussian Process models for ubiquitous user comfort preference sampling; global priors, active sampling and outlier rejection

ANN–GA smart appliance scheduling for optimised energy management in the domestic sector

Contact Info

Product

Resources

About