Anomaly detection in premise energy consumption data

Zhang, Yi; Chen, Weiwei; Black, Jason

doi:10.1109/pes.2011.6039858

Cited by 52 publications

(32 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Smart meters allow both residents to be more aware of their own energy consumption and electricity providers to have a better estimate on how much energy is needed in an area. Zhang et al [11] analyses energy consumption data on a household level to identify days when the residents have gone on vacation. They compare the accuracy of regression, entropy, and clustering based anomaly detection, with the regression based providing the best results.…”

Section: Related Workmentioning

confidence: 99%

Detection of Residents’ Abnormal Behaviour by Analysing Energy Consumption of Individual Households

Nordahl

Persson

Grahn

2017

2017 IEEE International Conference on Data Mining Workshops (ICDMW)

View full text Add to dashboard Cite

Abstract-As average life expectancy continuously rises, assisting the elderly population with living independently is of great importance. Detecting abnormal behaviour of the elderly living at home is one way to assist the eldercare systems with the increase of the elderly population. In this study, we perform an initial investigation to identify abnormal behaviour of household residents using energy consumption data. We conduct an experiment in two parts, the first to identify a suitable prediction algorithm to model energy consumption behaviour, and the second to detect abnormal behaviour. This approach allows for an initial step for the elderly care that has a low cost, is easily deployable, and is non-intrusive.

show abstract

Section: Related Workmentioning

confidence: 99%

Detection of Residents’ Abnormal Behaviour by Analysing Energy Consumption of Individual Households

Nordahl

Persson

Grahn

2017

2017 IEEE International Conference on Data Mining Workshops (ICDMW)

View full text Add to dashboard Cite

show abstract

“…Zhang et al [9] proposed several methods to detect anomalous days including regression, clustering, and entropy. They used temperature as an extra contextual information to increase accuracy.…”

Section: Power Anomaly Detection -Related Workmentioning

confidence: 99%

Spatio - Temporal Context Anomaly Detection for Residential Power Consumption

Sisworahardjo¹,

Saad²

2017

ijeei

View full text Add to dashboard Cite

Monitoring energy consumption and diagnosing abnormal behavior will enable utilities to introduce strategies to improve system resiliency, stability, and to meet energy efficiency targets. The deployment of advanced metering infrastructure (AMI) enables utilities to collect various raw data from its customers and networks. This paper presents contextual anomaly detection algorithm to detect irregular power consumption and visualize anomaly scores using unsupervised learning algorithm and temporal context generated from meter readings. The proposed algorithm computes an anomaly score for each user by considering historical consumption data. The anomaly score for a user is then adjusted by analyzing other contextual variables such as seasonal variation day of the week and other users with the same historical pattern. The implementation of realworld data set provided by power utility company shows a high performance of the proposed algorithm.

show abstract

“…Adnan et al combine linear regression with clustering techniques for getting better results [1]. Zhang et al [35] further use piecewise linear regression to fit the relation between energy consumption and weather temperature. The results obtained are more favorable than entropy and clustering methods.…”

Section: Related Workmentioning

confidence: 99%

“…Since abnormal consumption may also be resulted from user activities, such as using inefficient appliances, or over-lighting and working overtime in office buildings, anomalous feedback can warn energy consumers to minimize usage and help them identify inefficient appliances or over-lighting. Furthermore, anomaly detection can be used by utilities to establish the baseline of providing accurate demand-response programs to their customers [35]. Abnormal consumption detection is related to finding patterns in data where the statistical and data mining techniques are intensively used, e.g., [8,9,18,35], and it can perform close to or better than domain experts.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, anomaly detection can be used by utilities to establish the baseline of providing accurate demand-response programs to their customers [35]. Abnormal consumption detection is related to finding patterns in data where the statistical and data mining techniques are intensively used, e.g., [8,9,18,35], and it can perform close to or better than domain experts.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Online Anomaly Energy Consumption Detection Using Lambda Architecture

Liu

Iftikhar

Nielsen

et al. 2016

Big Data Analytics and Knowledge Discovery

View full text Add to dashboard Cite

Abstract. With the widely use of smart meters in the energy sector, anomaly detection becomes a crucial mean to study the unusual consumption behaviors of customers, and to discover unexpected events of using energy promptly. Detecting consumption anomalies is, essentially, a real-time big data analytics problem, which does data mining on a large amount of parallel data streams from smart meters. In this paper, we propose a supervised learning and statistical-based anomaly detection method, and implement a Lambda system using the in-memory distributed computing framework, Spark and its extension Spark Streaming. The system supports not only iterative refreshing the detection models from scalable data sets, but also real-time anomaly detection on scalable live data streams. This paper empirically evaluates the system and the detection algorithm, and the results show the effectiveness and the scalability of the lambda detection system.

show abstract

Anomaly detection in premise energy consumption data

Cited by 52 publications

References 7 publications

Detection of Residents’ Abnormal Behaviour by Analysing Energy Consumption of Individual Households

Detection of Residents’ Abnormal Behaviour by Analysing Energy Consumption of Individual Households

Spatio - Temporal Context Anomaly Detection for Residential Power Consumption

Online Anomaly Energy Consumption Detection Using Lambda Architecture

Contact Info

Product

Resources

About