Agent-based and graphical modelling of building occupancy

Liao, Chenda; Lin, Yashen; Barooah, Prabir

doi:10.1080/19401493.2010.531143

Cited by 130 publications

(74 citation statements)

References 18 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Particulate Matter (PM) sensor is shown to correlate well with the human movement [6]. PIR sensors and video camera sensors have also been proved to have strong correlations with human activities [7,8], and have been used a set of experiment to infer occupancy in different zones in a building. When individual types of sensors fail to give reliable performance on occupancy, sensor fusion is used which integrate the results from different sensors.…”

Section: A Presence Sensor and Occupancy Sensingmentioning

confidence: 99%

Virtual Occupancy Sensing: Using Smart Meters to Indicate Your Presence

Jin

Jia

Spanos

2017

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

Non-intrusive presence detection of individuals in commercial buildings is much easier to implement than intrusive methods such as passive infrared, acoustic sensors, and camera. Individual power consumption, while providing useful feedback and motivation for energy saving, can be used as a valuable source for presence detection. We conduct pilot experiments in an office setting to collect individual presence data by ultrasonic sensors, acceleration sensors, and WiFi access points, in addition to the individual power monitoring data. PresenceSense (PS), a semisupervised learning algorithm based on power measurement that trains itself with only unlabeled data, is proposed, analyzed and evaluated in the study. Without any labeling efforts, which are usually tedious and time consuming, PresenceSense outperforms popular models whose parameters are optimized over a large training set. The results are interpreted and potential applications of PresenceSense on other data sources are discussed. The significance of this study attaches to space security, occupancy behavior modeling, and energy saving of plug loads.

show abstract

Section: A Presence Sensor and Occupancy Sensingmentioning

confidence: 99%

Virtual Occupancy Sensing: Using Smart Meters to Indicate Your Presence

Jin

Jia

Spanos

2017

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

show abstract

“…By using previously developed stochastic models of occupant behaviour it is possible to predict agent behaviours based on solid empirical evidence. As an alternative to the BDI approach, Liao et al (2012) use room occupancy data to inform their agents' behaviours for the prediction of presence across multiple rooms and occupants. However, Liao et al note that for larger numbers of agents, it is often difficult to obtain high quality data from which to infer reliable rules.…”

Section: Multi-agent Simulationmentioning

confidence: 99%

On the multi-agent stochastic simulation of occupants in buildings

Chapman

Siebers

Robinson

2018

Journal of Building Performance Simulation

View full text Add to dashboard Cite

One of the principle causes for deviations between predicted and simulated performance of buildings relates to the stochastic nature of their occupants: their presence, activities whilst present, activity dependent behaviours and the consequent implications for their perceived comfort. A growing research community is active in the development and validation of stochastic models addressing these issues; and considerable progress has been made. Specifically models in the areas of presence, activities while present, shading devices, window openings and lighting usage.One key outstanding challenge relates to the integration of these prototype models with building simulation in a coherent and generalizable way; meaning that emerging models can be integrated with a range of building simulation software. This thesis describes our proof of concept platform that integrates stochastic occupancy models within a multi agent simulation platform, which communicates directly with building simulation software. The tool is called Nottingham Multi-Agent Stochastic Simulation (No-MASS).No-MASS is tested with a building performance simulation solver to demonstrate the effectiveness of the integrated stochastic models on a residential building and a non-residential building. To account for diversity between occupants No-MASS makes use of archetypical behaviours within the stochastic models of windows, shades and activities. Thus providing designers with means to evaluate the performance of their designs in response to the range of expected behaviours and to evaluate the robustness of their design solutions; which is not possible using current simplistic deterministic representations. No-MASS employs agent machine learning techniques that allow them to learn how to respond to the processes taking place within a building and agents can choose a strategy without the need for context specific rules.Employing these complementary techniques to support the comprehensive simulation of occupants presence and behaviour, integrated within a single platform that can readily interface with a range of building (and urban) energy simulation programs is the key contribution to knowledge from this thesis. Nevertheless, there is significant scope to extend this work to further reduce the performance gap between simulated and real world buildings.

show abstract

“…Of them, Page's model [1] and Multiple Modules (MUMO) model [2] are the advanced versions for occupancy prediction by combining stochastic process with agents based modeling. Nevertheless, Page's model and MUMO model are more likely to be applicable to building control systems of existing buildings rather than space planning.…”

Section: Current Occupancy and Space Use Modelsmentioning

confidence: 99%

“…Categorizing occupants in detail by their varying characteristics with particular attributes is the way of achieving a more reliable occupant behavior model. On a building scale, for instance, Liao [12] groups users into primary users and secondary occupants according to occupation in order to discern the length of stay of occupants. Tabak [5] also uses personal data, like roles, organizational unit, and FTE (full-time equivalence), to model an activity-based occupancy model.…”

Section: B Individual Heterogeneitymentioning

confidence: 99%

A Conceptual Framework for Developing Indoor Spatial Choice Model

H.¹,

Kim²

2014

IJET

View full text Add to dashboard Cite

Abstract-Detailed space use analysis for a building is needed in the near future for building energy efficiency and effective space planning. In this regard, the development of an indoor spatial choice model is indispensable for better space use prediction. However, research efforts into the model are still insufficient in this area. As an initial study, this paper reviews spatial choice behavior, and proposes a conceptual framework that displays the necessary development steps, behavioral rules, and required data for developing indoor spatial choice model. Finally, future opportunities and challenges are discussed.Index Terms-Occupant behavior, space use analysis, spatial choice model, space planning.

show abstract

Agent-based and graphical modelling of building occupancy

Cited by 130 publications

References 18 publications

Virtual Occupancy Sensing: Using Smart Meters to Indicate Your Presence

Virtual Occupancy Sensing: Using Smart Meters to Indicate Your Presence

On the multi-agent stochastic simulation of occupants in buildings

A Conceptual Framework for Developing Indoor Spatial Choice Model

Contact Info

Product

Resources

About