Abnormal behaviour analysis algorithm for electricity consumption based on density clustering

Xiang, Min; Rao, Huayang; Tan, Tong; Wang, Zaiqian; Ma, Yue

doi:10.1049/joe.2018.5123

Cited by 12 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5 GHz with 32 GB of RAM. The testing in this work is conducted using the Ohio State University-provided OTCBVS Benchmark Dataset database [16] and Terravic Motion IR Database database [17]. All ROIs are normalised to 32×32 to ensure that the test set and training set are of the same size.…”

Section: Resultsmentioning

confidence: 99%

Identification of Unusual Visitor Activity Using a Hybrid Gaussian Model in Picturesque Locations

Aziguli Abudouwaili

2024

jes

View full text Add to dashboard Cite

The management of tourists in picturesque locations is becoming increasingly crucial due to the rapid growth of the tourism industry. The subsequent issue, though, is the rise in strange visitor behaviours, like carelessly crossing hazardous locations and doing illicit graffiti, among other things. These strange behaviours harm tourist destinations' reputations while also raising the possibility of safety hazards. Because of this, this paper uses a regional feature analysis approach to detect abnormal pedestrian behaviour. Specifically, we begin by modelling the background, obtain the moving target region information through moving target detection, and use the minimum outer rectangular box as the regional feature. Lastly, we compute the aspect ratio of this rectangle, perform curve fitting and prediction, and finally conclude the abnormal behaviour detection process. The method's simplicity and speed are demonstrated by the experimental findings.

show abstract

Section: Resultsmentioning

confidence: 99%

Identification of Unusual Visitor Activity Using a Hybrid Gaussian Model in Picturesque Locations

Aziguli Abudouwaili

2024

jes

View full text Add to dashboard Cite

show abstract

“…Identifying consumption abnormalities was highlighted as a real‐time extensive data analysis issue by the authors of ref. [11]. Furthermore, utilising the in‐memory distributed computing framework Spark and its extension Spark Streaming, the author developed a supervised learning and statistical‐based anomaly detection method and implemented a lambda system.…”

Section: Related Workmentioning

confidence: 99%

An embedded and intelligent anomaly power consumption detection system based on smart metering

Qaddoori

Ali

2023

IET Wireless Sensor Systems

View full text Add to dashboard Cite

User behaviour, human mistakes, and underperforming equipment contribute to wasted energy in buildings and industries. Identifying anomalous consumption power behaviour can help to reduce peak energy usage and change undesirable user behaviour. Furthermore, decreasing energy consumption in buildings is difficult because usage patterns vary from one building to the next. So, the main contribution in this manuscript is to propose a lightweight architecture for smart meter to identify abnormalities in power consumption for each building individually using machine learning (ML) models and implement on a Single Board Computer. To detect daily and periodic pattern anomalies, two models of anomaly detection based on supervised and unsupervised ML algorithms are built and trained where numerous algorithms were utilised to select the best algorithm for each model. Also, the proposed approach enables iterative procedure modifications by retraining the two anomaly detection models on data aggregator server based on the received data meter from the specific smart meter to give better power service to clients while minimising provider losses. The effectiveness and efficiency of the suggested approach have been proven through extensive analysis.

show abstract

“…Clustering divides objects into several subsets through some specific algorithms, so that objects in the same subset have some similar attributes. In many researches, clustering algorithm is used to identify power theft based on the data features of different users [4][5][6][7][8][9][10] . Different clusters represent different types of power users, and the same type of power users shares similar power consumption patterns.…”

Section: Clustering Analysis To Recover Power Loss Due To Power Stealingmentioning

confidence: 99%

Identify power stealing time period based on user power consumption data

Xie

Wang

Liu

et al. 2023

International Conference on Computer Application and Information Security (ICCAIS 2022)

View full text Add to dashboard Cite

In order to recover the loss of the stolen electric power, a comprehensive approach by analyzing the user power consumption data has been developed. According to the characteristics of the power stealing methods of each category of users, a comprehensive algorithm is employed to identify the method and the length of the power stealing behaviors. Abnormal data series that meet the power stealing characteristics for voltage, current, power and power factor are classified. Clustering algorithm is employed to identify abnormal power consumption, such that time period of power stealing can be calculated. Classification and clustering algorithms are synthesized such that results of different algorithms with different principles can be cross-verified, and stolen power can be recovered accurately and fairly.

show abstract

Abnormal behaviour analysis algorithm for electricity consumption based on density clustering

Cited by 12 publications

References 13 publications

Identification of Unusual Visitor Activity Using a Hybrid Gaussian Model in Picturesque Locations

Identification of Unusual Visitor Activity Using a Hybrid Gaussian Model in Picturesque Locations

An embedded and intelligent anomaly power consumption detection system based on smart metering

Identify power stealing time period based on user power consumption data

Contact Info

Product

Resources

About