A Large-Scale Replication of Smart Grids Power Consumption
Anomaly Detection

D 2020

A Large-Scale Replication of Smart Grids Power Consumption Anomaly Detection

ROSSI, Bruno

Základní údaje

Originální název

A Large-Scale Replication of Smart Grids Power Consumption Anomaly Detection

Autoři

ROSSI, Bruno (380 Itálie, garant, domácí)

Vydání

Setubal, Portugal, Proceedings of the 5th International Conference on Internet of Things, Big Data and Security (IoTBDS), od s. 288-295, 8 s. 2020

Nakladatel

SciTePress

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Odkazy

URL

Kód RIV

RIV/00216224:14610/20:00115322

Organizační jednotka

Ústav výpočetní techniky

ISBN

978-989-758-426-8

DOI

https://doi.org/10.5220/0009396402880295

UT WoS

000615960700030

EID Scopus

2-s2.0-85089466759

Klíčová slova anglicky

Smart Grids; Smart Meters; Anomaly Detection; Power Consumption; Replication Study

Štítky

rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 27. 4. 2021 12:21, doc. Bruno Rossi, PhD

Anotace

V originále

Anomaly detection plays a significant role in the area of Smart Grids: many algorithms were devised and applied, from intrusion detection to power consumption anomalies identification. In this paper, we focus on detecting anomalies from smart meters power consumption data traces. The goal of this paper is to replicate to a much larger dataset a previously proposed approach by Chou and Telaga (2014) based on ARIMA models. In particular, we investigate different model training approaches and the distribution of anomalies, putting forward several lessons learned. We found the method applicable also to the larger dataset. Fine-tuning the parameters showed that adopting an accumulating window strategy did not bring benefits in terms of RMSE. While a 2s rule seemed too strict for anomaly identification for the dataset.

Návaznosti

EF16_013/0001802, projekt VaV

Název: CERIT Scientific Cloud

LM2015085, projekt VaV

Název: CERIT Scientific Cloud (Akronym: CERIT-SC)

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, CERIT Scientific Cloud

Citovat

ROSSI, Bruno. A Large-Scale Replication of Smart Grids Power Consumption Anomaly Detection. Online. In Gary Wills, Péter Kacsuk, and Victor Chang. Proceedings of the 5th International Conference on Internet of Things, Big Data and Security (IoTBDS). Setubal, Portugal: SciTePress, 2020, s. 288-295. ISBN 978-989-758-426-8. Dostupné z: https://doi.org/10.5220/0009396402880295.

@inproceedings{1621536,
   author = {Rossi, Bruno},
   address = {Setubal, Portugal},
   booktitle = {Proceedings of the 5th International Conference on Internet of Things, Big Data and Security (IoTBDS)},
   doi = {https://doi.org/10.5220/0009396402880295},
   editor = {Gary Wills, Péter Kacsuk, and Victor Chang},
   keywords = {Smart Grids; Smart Meters; Anomaly Detection; Power Consumption; Replication Study},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Setubal, Portugal},
   isbn = {978-989-758-426-8},
   pages = {288-295},
   publisher = {SciTePress},
   title = {A Large-Scale Replication of Smart Grids Power Consumption Anomaly Detection},
   url = {https://www.scitepress.org/PublicationsDetail.aspx?ID=38neH0VRHoA=&t=1},
   year = {2020}
}

TY  - CONF
ID  - 1621536
AU  - Rossi, Bruno
PY  - 2020
TI  - A Large-Scale Replication of Smart Grids Power Consumption Anomaly Detection
PB  - SciTePress
CY  - Setubal, Portugal
SN  - 9789897584268
KW  - Smart Grids
KW  - Smart Meters
KW  - Anomaly Detection
KW  - Power Consumption
KW  - Replication Study
UR  - https://www.scitepress.org/PublicationsDetail.aspx?ID=38neH0VRHoA=&t=1
N2  - Anomaly detection plays a significant role in the area of Smart Grids: many algorithms were devised and applied, from intrusion detection to power consumption anomalies identification. In this paper, we focus on detecting anomalies from smart meters power consumption data traces. The goal of this paper is to replicate to a much larger dataset a previously proposed approach by Chou and Telaga (2014) based on ARIMA models. In particular, we investigate different model training approaches and the distribution of anomalies, putting forward several lessons learned. We found the method applicable also to the larger dataset. Fine-tuning the parameters showed that adopting an accumulating window strategy did not bring benefits in terms of RMSE. While a 2s rule seemed too strict for anomaly identification for the dataset.
ER  -

ROSSI, Bruno. A Large-Scale Replication of Smart Grids Power Consumption Anomaly Detection. Online. In Gary Wills, Péter Kacsuk, and Victor Chang. \textit{Proceedings of the 5th International Conference on Internet of Things, Big Data and Security (IoTBDS)}. Setubal, Portugal: SciTePress, 2020, s.~288-295. ISBN~978-989-758-426-8. Dostupné z: https://doi.org/10.5220/0009396402880295.

Přehled o publikaci