Smart Meter Data Analytics for Occupancy Detection of Buildings with Renewable Energy Generation

Allik, Alo; Muiste, Siim; Pihlap, Heino

doi:10.1109/icrera49962.2020.9242830

Cited by 8 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in most cases, a ground truth (even small) is necessary to understand when the space is occupied. For this reason, Allik et al [56] suggest that without ground truth a simple yet reasonable way to understand occupancy is analysing the standard deviation within the hour during nighttime (from 11 pm to 5 am) when people are usually inactive and sleeping, and to assume that the third quartile can be the threshold to detect the presence of people during daytime. This threshold is thus used as a detector in the database, resulting in an unoccupied (0) and occupied (1) value for each hour.…”

Section: Schedules Creation Proceduresmentioning

confidence: 99%

UBEM's archetypes improvement via data-driven occupant-related schedules randomly distributed and their impact assessment

Ferrando

Ferroni

Pelle

et al. 2022

Sustainable Cities and Society

View full text Add to dashboard Cite

Section: Schedules Creation Proceduresmentioning

confidence: 99%

UBEM's archetypes improvement via data-driven occupant-related schedules randomly distributed and their impact assessment

Ferrando

Ferroni

Pelle

et al. 2022

Sustainable Cities and Society

View full text Add to dashboard Cite

“…1 graph of [22] nodes 2 graphs of [11,11] nodes 4 graphs of [6,5,6,5] nodes 6 graphs of [3,3,5,3,3,5] nodes…”

Section: λ Eigenvectors and Associated Values Of L;mentioning

confidence: 99%

“…All the applications mentioned above do not account for the fact that SM data contains, by nature, sensitive information such as occupancy (which can potentially be predicted [19,20,21,22,23]). For this reason, data privacy has to be tackled from a regulatory perspective [24] and from a technical perspective [25].…”

Section: Introductionmentioning

confidence: 99%

Privacy-preserving methods for smart-meter-based network simulations

Holweger¹,

Bloch²,

Ballif³

et al. 2021

Preprint

View full text Add to dashboard Cite

Smart-meters are a key component of energy transition. The large amount of data collected in near real-time allows grid operators to observe and simulate network states. However, privacy-preserving rules forbid the use of such data for any applications other than network operation and billing. Smartmeter measurements must be anonymised to transmit these sensitive data to a third party to perform network simulation and analysis. This work proposes two methods for data anonymisation that enable the use of raw active power measurements for network simulation and analysis. The first is based on an allocation of an externally sourced load database. The second consists of grouping smart-meter data with similar electric characteristics, then performing a random permutation of the network load-bus assignment. A benchmark of these two methods highlights that both provide similar results in bus-voltage magnitude estimation concerning ground-truth voltage.

show abstract

“…Specifically, in [22] a machine learning based solution utilizing Random Forests (RF) as classifier for occupancy detection is presented. Furthermore, the approaches in [23,24] present advanced occupancy estimations for limited ground truth data [23] and under consideration of renewable energy generation within the same household [24]. Moreover, an extensive comparison of machine learning classifiers with optimal hyperparameters was presented in [25].…”

Section: Introductionmentioning

confidence: 99%

On the non-intrusive extraction of residents’ privacy- and security-sensitive information from energy smart meters

Schirmer

Mporas

2021

Neural Comput & Applic

View full text Add to dashboard Cite

Energy smart meters have become very popular in monitoring and smart energy management applications.However, the acquired measurements except the energy consumption information may also carry information about the residents' daily routine, preferences and profile. In this article we investigate the potential of extracting information from smart meters related to residents' security and privacy sensitive information. Specifically, using methodologies for load demand prediction, non-intrusive load monitoring and elastic matching, evaluation of extraction of information related to house occupancy, multimedia watching detection, socioeconomic and health profiling of residents was performed. The evaluation results showed that the aggregated energy consumption signals contain information related to residents' privacy and security, which can be extracted from the smart meter measurements.

show abstract

Smart Meter Data Analytics for Occupancy Detection of Buildings with Renewable Energy Generation

Cited by 8 publications

References 14 publications

UBEM's archetypes improvement via data-driven occupant-related schedules randomly distributed and their impact assessment

UBEM's archetypes improvement via data-driven occupant-related schedules randomly distributed and their impact assessment

Privacy-preserving methods for smart-meter-based network simulations

On the non-intrusive extraction of residents’ privacy- and security-sensitive information from energy smart meters

Contact Info

Product

Resources

About