Model predictive HVAC control with online occupancy model

Dobbs, Justin R.; Hencey, Brandon

doi:10.1016/j.enbuild.2014.07.051

Cited by 86 publications

(24 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hailemariam, et al,2011 andSzczurek et al, 2017). Similarly, Mahdavi (2009), Dobbs andHencey (2014) and Oldewurtel et al (2013) have also extensively highlighted the importance of occupancy number as well as their behaviour in building energy consumption, building performance simulation and building control. Studies such as Erickson et al (2014) and Dong and Andrews (2009) have shown that around one-third of the energy consumed in the buildings can be saved using occupancy-based control.…”

Section: Introductionmentioning

confidence: 98%

A Machine Learning Approach on Occupant Number Prediction for Indoor Spaces

Işıkdağ¹,

Sahin²,

Cansiz³

2018

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

<p><strong>Abstract.</strong> The knowledge about the occupancy of an indoor space can serve to various domains ranging from emergency response to energy efficiency in buildings. The literature in the field presents various methods for occupancy detection. Data gathered for occupancy detection, can also be used to predict the number of occupants at a certain indoor space and time. The aim of this research was to determine the number of occupants in an indoor space, through the utilisation of information acquired from a set of sensors and machine learning techniques. The sensor types used in this research was a sound level sensor, temperature/humidity level sensor and an air quality level sensor. Based on data acquired from these sensors six automatic classification techniques are employed and tested with the aim of automatically detecting the number of occupants in an indoor space by making use of multi-sensor information. The results of the tests demonstrated that machine learning techniques can be used as a tool for prediction of number of occupants in an indoor space.</p>

show abstract

Section: Introductionmentioning

confidence: 98%

A Machine Learning Approach on Occupant Number Prediction for Indoor Spaces

Işıkdağ¹,

Sahin²,

Cansiz³

2018

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s on occupant comfort [1,3,4]. Apart from time, occupancy can be skewed across space as well -i.e., different areas within a zone can have different occupancy levels at the same time.…”

Section: Introductionmentioning

confidence: 99%

On the Utility of Occupancy Sensing for Managing HVAC Energy in Large Zones

Nagarathinam

Iyer

Vasan

et al. 2015

Proceedings of the 2015 ACM Sixth International Conference on Future Energy Systems

View full text Add to dashboard Cite

HVAC control strategies that exploit temporal variations in zone occupancy have been well studied. Occupancy can also vary spatially within a zone, especially during off-design operating conditions. We complement prior work by studying the usefulness of sensing occupancy information at different spatial resolutions in large zones served by multiple AHUs. As conventional PID controllers cannot utilize this information effectively, we propose a new control strategy and study the usefulness of sensing. We observe that utility of sensing occupancy at finer spatial resolutions is higher when the actual spatial heterogeneity in occupancy is higher.

show abstract

“…The results from the two studies were consistent and showed that measurements were sufficient for achieving energy savings around 50% in comparison to conventional controllers, while only small additional gains were provided through prognosis. Forecasts of indoor climate disturbances for control applications were also considered in [15] and [16], but with the focus on models for improving predictions. While [15] considered a self-tuning occupancy prediction model, [16] aimed to account for uncertainties in the control, and both investigations showed that their algorithms were beneficial.…”

Section: Introductionmentioning

confidence: 99%

Energy efficient climate control in office buildings without giving up implementability

2015

View full text Add to dashboard Cite

h i g h l i g h t sThe principle of model-based controller for indoor climate control was adopted. A simplified version was presented and evaluated through experiments. A typical office working day was re-created in a test facility. Experiments were conducted for two weather seasons and two types of office rooms. Energy usage was reduced at the same time as the indoor climate was improved. Keywords:Office buildings Indoor climate control Implementability Air-based heating and cooling Energy efficiency Model-based controller a b s t r a c tThe adaptation between a building and its automation system can potentially be increased by model-based controllers with an integrated control model and information about indoor climate disturbances. The associated energy savings potential is large but a widespread utilization is typically prevented by high complexities. From that point of view, a trade-off technology that combines implementability with an overall higher performance than the system of current practice would be a better option at most sites. This work presents an experimental evaluation of an alternative controller that follows the same principle as model-based, but has gone through a large number of simplification measures for a reduced overall complexity and a limited function. The controller was evaluated for indoor climate control by automating the ventilation flow rate during a typical office working day that was re-created in a laboratory environment. Experiments were conducted in two different office sites, as well as during two weather seasons of Swedish summer and winter. From the investigation, it was concluded that despite of the reduced complexity, the investigated controller could save between 12% and 19% of indicated energy compared to a system of common practice at the same time as the quality of indoor climate was maintained.

show abstract

Model predictive HVAC control with online occupancy model

Cited by 86 publications

References 19 publications

A Machine Learning Approach on Occupant Number Prediction for Indoor Spaces

A Machine Learning Approach on Occupant Number Prediction for Indoor Spaces

On the Utility of Occupancy Sensing for Managing HVAC Energy in Large Zones

Energy efficient climate control in office buildings without giving up implementability

Contact Info

Product

Resources

About