Contextual occupancy detection for smart office by pattern recognition of electricity consumption data

Akbar, Adnan; Nati, Michele; Carrez, François; Moessner, Klaus

doi:10.1109/icc.2015.7248381

Cited by 47 publications

(33 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…If due to some failure, we miss a reading, we keep the previous valid one. This approach is common to mimic the constant consumption of simple devices, such as LCD monitors [13]. We then analyze the recorded data to attest the system performance.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Power-Based Device Recognition for Occupancy Detection

Pratama

Widyawan

Lazovik

et al. 2018

Service-Oriented Computing – ICSOC 2017 Workshops

View full text Add to dashboard Cite

Each person using electrical devices leaves electricity fingerprints in the form of power consumption. These can be very useful for understanding the context of that person in, for instance, a smart office. A device that is highly correlated with the presence of a person in an office is the computer monitor; the correlation is in the range 83-96%. Therefore, it is useful to recognize from an aggregated power load the portion that is due to computer monitors. In this paper, we propose an event-based device recognition approach. After studying several predictors and features for device classification, we build a prototype for the classification. We evaluate the approach with actual power measurement of seven office monitors used by four workers in an office environment. Our experiments show that the approach is feasible and the per-day accuracy ranges in the range 69-80% for seven and five physical devices, respectively.

show abstract

Section: Discussionmentioning

confidence: 99%

“…An effort to classify personal occupancy in the office was developed by [13]. The authors deploy one power measurement on each work desk and classify whether the respective occupant is present, away, or in standby.…”

Section: Related Workmentioning

confidence: 99%

Power-Based Device Recognition for Occupancy Detection

Pratama

Widyawan

Lazovik

et al. 2018

Service-Oriented Computing – ICSOC 2017 Workshops

View full text Add to dashboard Cite

show abstract

“…For example, measurements were conducted [19,20] with the aim of obtaining occupancy states from metered electricity usage. This kind of implementation is clearly limited to modern buildings already equipped with .…”

Section: Measurementsmentioning

confidence: 99%

Occupant behavior: a â€œnewâ€ factor in energy performance of buildings. Methods for its detection in houses and in offices.

Simone

Fajilla

2019

JWA

View full text Add to dashboard Cite

The role that occupants have on energy consumption and performance of buildings is known, but still requires a great deal of research. In this paper, the most common techniques to detect occupancy and occupant behavior in buildings are categorized with their advantages and disadvantages. Being the buildings characterized by different energy usage, the presentation of the studies that applied surveys and monitoring campaigns is conducted with differentiation between residential and office buildings.

show abstract

“…It was found that the algorithm has an average estimation accuracy of 80.78% and outperforms the other previously mentioned methods. A method based on electricity data consumption with an occupancy detection rate of 94% is presented in [37].…”

Section: Algorithms For Occupancy Detectionmentioning

confidence: 99%

A Web-Based Office Climate Control System Using Wireless Sensors

et al. 2016

View full text Add to dashboard Cite

Abstract-Conventional heating, ventilating, and air conditioning (HVAC) systems usually achieve the desired control level by means of simple ON-OFF control, which can often result in high energy wastage. A potential solution to this issue is intelligent self-regulating HVAC controllers, which base their actions/decisions on sensor data. In this paper, an office climate monitoring and control system is designed and implemented. The system consists of various wireless sensor nodes and a control node. The sensor nodes provide the sensor data necessary to determine occupancy and the control node executes the algorithm, which decides whether to activate cooling or heating based on the sensor data. This system can serve as a controller and can be integrated into HVAC systems in smart buildings. It is shown that the developed control algorithm executed on the control node results in an improvement of up to 39% in energy efficiency over conventional ON-OFF controllers for HVAC systems.

show abstract

Contextual occupancy detection for smart office by pattern recognition of electricity consumption data

Cited by 47 publications

References 13 publications

Power-Based Device Recognition for Occupancy Detection

Power-Based Device Recognition for Occupancy Detection

Occupant behavior: a â€œnewâ€ factor in energy performance of buildings. Methods for its detection in houses and in offices.

A Web-Based Office Climate Control System Using Wireless Sensors

Contact Info

Product

Resources

About

Contextual occupancy detection for smart office by pattern recognition of electricity consumption data

Cited by 47 publications

References 13 publications

Power-Based Device Recognition for Occupancy Detection

Power-Based Device Recognition for Occupancy Detection

Occupant behavior: a â€œnewâ€ factor in energy performance of buildings. Methods for its detection in houses and in offices.

A Web-Based Office Climate Control System Using Wireless Sensors

Contact Info

Product

Resources

About

Occupant behavior: a â€œnewâ€ factor in energy performance of buildings. Methods for its detection in houses and in offices.