Data analytics for occupancy pattern learning to reduce the energy consumption of HVAC systems in office buildings

Capozzoli, Alfonso; Piscitelli, Marco Savino; Gorrino, Alice; Ballarini, Ilaria; Corrado, Vincenzo

doi:10.1016/j.scs.2017.07.016

Cited by 100 publications

(35 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…What's more, occupancy behavior can also be leveraged to reduce energy consumption, such as opening a window. In [49], the study reconfigured the occupant sub-areas based on similar arrival and departure times.…”

Section: Discussionmentioning

confidence: 99%

An Overview of Real-time Occupancy Information Acquisition Method for Demand-driven Building Energy Management

Liu¹,

Luo²,

Zhang³

2019

Proceedings of the Creative Construction Conference 2019

View full text Add to dashboard Cite

Efficient building energy management needs to meet both energy savings and user comfort requirements, which relies on the accurate acquisition of occupancy information over time. In order to meet the data requirements of different building application environments, this paper reviews different sensor technologies based on the principle of obtaining occupancy information, and divides them into five categories, namely motion sensors, environmental sensors, radio frequency (RF) sensors, camera, and contextual sensors. A review of the fusion of multiple sensors that have been widely used for building occupancy detection in recent years has also been conducted. The pros and cons of the prior art are discussed in detail, thus future research can better fit the needs of different system control (such as heating, ventilation, and air conditioning (HVAC) and lighting systems) in different types of buildings.

show abstract

Section: Discussionmentioning

confidence: 99%

An Overview of Real-time Occupancy Information Acquisition Method for Demand-driven Building Energy Management

Liu¹,

Luo²,

Zhang³

2019

Proceedings of the Creative Construction Conference 2019

View full text Add to dashboard Cite

show abstract

“…Predictive applications include building energy use and demand prediction (Ahmed et al, 2011;Wang & Srinivasan, 2017;Zhao & Magoulès, 2012), prediction of building occupancy and occupant behaviour (D'Oca & Hong, 2014;Zhao et al, 2014), and fault detection diagnostics for building systems (Cheng et al, 2016;Pena et al, 2016). Descriptive tasks, on the other hand, are concerned with framework development (D'Oca & Hong, 2015;Fan et al, 2015aFan et al, , 2015bPark et al, 2016;Yu et al, 2013;Zhou et al, 2015), patterns in occupant behaviour (Capozzoli et al, 2017), building modelling and optimal control (Xiao & Fan, 2014), as well as discovering and understanding energy use patterns (Gaitani et al, 2010;Miller et al, 2015;Wu and Clements-Croome, 2007). Other efforts include the use of data mining for high-performance building design based on classification models for sustainability certification evaluation (Jun & Cheng, 2017), use of BIM-based data mining approaches for improvement of facility management (Peng et al, 2017), use of semantic modelling, neural networks and data mining algorithms for building energy management (McGlinn et al, 2017), etc.…”

Section: Related Workmentioning

confidence: 99%

Towards data-driven sustainable design: decision support based on knowledge discovery in disparate building data

Petrova

Pauwels

Svidt

et al. 2018

Architectural Engineering and Design Management

View full text Add to dashboard Cite

Sustainable building design requires an interplay between multidisciplinary input and fulfilment of diverse criteria to align into one high-performing whole. BIM has already brought a profound change in that direction, by allowing execution of efficient collaborative workflows. However, design decision-making still relies heavily on rules of thumb and previous experiences, and not on sound evidence. To improve the design process and effectively build towards a sustainable future, we need to rely on the multiplicity of data available from our existing building stock. The objective of this research is, therefore, to transform existing data, discover new knowledge and inform future design decision-making in an evidence-based manner. This article looks specifically into this task by (1) outlining and distinguishing between the diverse building data sources and types, (2) indicating how the data can be analysed, (3) demonstrating how the discovered knowledge can be implemented in a semantic integration layer and (4) how it can be brought back to design professionals through the design aids they use. We, therefore, propose a performance-oriented design decision support system, relying on BIM, data mining and semantic data modelling, thereby allowing customised information retrieval according to a defined goal.

show abstract

“…Smart buildings have long been a target of efforts aiming to reduce energy consumption, improve occupant comfort, and increase operational efficiency. Although a substantial body of work advances the state-of-the-art-including automated control (Piette et al, 2009;Sturzenegger et al, 2012;Capozzoli et al, 2017), modeling (Privara et al, 2013) and analysis (Schein et al, 2006;Jahn et al, 2011)-such approaches do not see widespread use due to the prohibitive cost of configuring their instantiation to each building. A major factor in this cost is due to lack of interoperability standards; without such standards, the rollout of energy efficiency measures involves customizing implementations to the one-off combinations of hardware and software configurations that are unique to each building.…”

Section: Introductionmentioning

confidence: 99%

Formalizing Tag-Based Metadata With the Brick Ontology

Fierro

Koh

Nagare

et al. 2020

Front. Built Environ.

View full text Add to dashboard Cite

Current efforts establishing semantic metadata standards for the built environment span academia, industry and standards bodies. For these standards to be effective, they must be clearly defined and easily extensible, encourage consistency in their usage, and integrate cleanly with existing industrial standards, such as BACnet. There is a natural tension between informal tag-based systems that rely upon idiom and convention for meaning, and formal ontologies amenable to automated tooling. We present a qualitative analysis of Project Haystack, a popular tagging system for building metadata, and identify a family of inherent interpretability and consistency issues in the tagging model that stem from its lack of a formal definition. To address these issues, we present the design and implementation of the Brick+ ontology, a drop-in replacement for Brick with clear formal semantics that enables the inference of a valid Brick model from an informal Haystack model, and demonstrate this inference across five Haystack models.

show abstract

Data analytics for occupancy pattern learning to reduce the energy consumption of HVAC systems in office buildings

Cited by 100 publications

References 40 publications

An Overview of Real-time Occupancy Information Acquisition Method for Demand-driven Building Energy Management

An Overview of Real-time Occupancy Information Acquisition Method for Demand-driven Building Energy Management

Towards data-driven sustainable design: decision support based on knowledge discovery in disparate building data

Formalizing Tag-Based Metadata With the Brick Ontology

Contact Info

Product

Resources

About