Publications - Pervasive Computing Laboratory

 Access control anotacionsemantica authentication Cloud computing coap compromise cryptography cynamon emadrid emrisco home network I-Shaper identity management inrisco inteligenciafuentesabiertas Internet of Things IoT magos Pervasive computing privacy Protocols Qursa raudo2 Security servicioseguridad Smart Card Trust management Ubisec VANETs 
Show all
2022
 García-Rubio, Carlos;  Campo, Celeste;  Moure-Garrido, Marta
Synthetic Generation of Electrical Consumption Traces in Smart Homes Conference 
 Lecture Notes in Networks and Systems, vol. 594, Springer International Publishing, 2022, ISBN: 978-3-031-21332-8.
Abstract | Links | BibTeX | Tags: anomaly detection, compromise, cynamon, Electricity consumption, magos, Smart home, Synthetic dataset generation
@conference{garciarubio008,

title = {Synthetic Generation of Electrical Consumption Traces in Smart Homes},

author = {Carlos García-Rubio and Celeste Campo and Marta Moure-Garrido },

url = {https://link.springer.com/chapter/10.1007/978-3-031-21333-5_68},

doi = {https://doi.org/10.1007/978-3-031-21333-5_68},

isbn = {978-3-031-21332-8},

year  = {2022},

date = {2022-11-21},

urldate = {2022-11-21},

booktitle = { Lecture Notes in Networks and Systems},

volume = {594},

pages = {681-692},

publisher = {Springer International Publishing},

abstract = {With the introduction of the smart grid, smart meters and smart plugs, it is possible to know the energy consumption of a smart home, either per appliance or aggregate. Some recent works have used energy consumption traces to detect anomalies, either in the behavior of the inhabitants or in the operation of some device in the smart home. To train and test the algorithms that detect these anomalies, it is necessary to have extensive and well-annotated consumption traces. However, this type of traces is difficult to obtain. In this paper we describe a highly configurable synthetic electrical trace generator, with characteristics similar to real traces, that can be used in this type of study. In order to have a more realistic behavior, the traces are generated by adding the consumption of several simulated appliances, which precisely represent the consumption of different typical electrical devices. Following the behavior of the real traces, variations at different scales of time and anomalies are introduced to the aggregated smart home energy consumption.},

keywords = {anomaly detection, compromise, cynamon, Electricity consumption, magos, Smart home, Synthetic dataset generation},

pubstate = {published},

tppubtype = {conference}

}

Close
With the introduction of the smart grid, smart meters and smart plugs, it is possible to know the energy consumption of a smart home, either per appliance or aggregate. Some recent works have used energy consumption traces to detect anomalies, either in the behavior of the inhabitants or in the operation of some device in the smart home. To train and test the algorithms that detect these anomalies, it is necessary to have extensive and well-annotated consumption traces. However, this type of traces is difficult to obtain. In this paper we describe a highly configurable synthetic electrical trace generator, with characteristics similar to real traces, that can be used in this type of study. In order to have a more realistic behavior, the traces are generated by adding the consumption of several simulated appliances, which precisely represent the consumption of different typical electrical devices. Following the behavior of the real traces, variations at different scales of time and anomalies are introduced to the aggregated smart home energy consumption.
Close
https://link.springer.com/chapter/10.1007/978-3-031-21333-5_68
doi:https://doi.org/10.1007/978-3-031-21333-5_68
Close