Feature Extraction of Anomaly Electricity Usage Behavior in Residence Using Autoencoder

• Published in: Electronics (Basel) Vol. 11; no. 9; p. 1450
• Main Authors: Tsai, Chia-Wei, Chiang, Kuei-Chun, Hsieh, Hsin-Yuan, Yang, Chun-Wei, Lin, Jason, Chang, Yao-Chung
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.05.2022
• Subjects: Accuracy; Advanced metering infrastructure; Anomalies; Artificial intelligence; Behavior; Carbon; Data acquisition; Deep learning; Electricity; Electricity consumption; Electricity meters; Energy conservation; Energy consumption; Energy management; Feature extraction; Internet of Things; Load; Machine learning; Residential energy; Taiwan
• ISSN: 2079-9292; 2079-9292
• DOI: 10.3390/electronics11091450

Due to the climate crisis, energy-saving issues and carbon reduction have become the top priority for all countries. Owing to the increasing popularity of advanced metering infrastructure and smart meters, the cost of acquiring data on residential electricity consumption has substantially dropped. This change promotes the analysis of residential electricity consumption, which features both small and complicated consumption behaviors, using machine learning to become an important research topic among various energy saving and carbon reduction measures. The main subtopic of this subject is the identification of abnormal electricity consumption behaviors. At present, anomaly detection is typically realized using models based on low-level features directly collected by sensors and electricity meters. However, due to the significant number of dimensions and a large amount of redundant information in these low-level features, the training efficiency of the model is often low. To overcome this, this study adopts an autoencoder, which is a deep learning technology, to extract the high-level electricity consumption information of residential users to improve the anomaly detection performance of the model. Subsequently, this study trains one-class SVM models for anomaly detection by using the high-level features of five actual residential users to verify the benefits of high-level features.