An Anomaly Detection Scheme based on LSTM Autoencoder for Energy Management
| Autor: | Jong-Won Park, Youn-Kwae Jeong, Hong-Soon Nam |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Scheme (programming language)
Multivariate statistics business.industry Computer science Energy management 020209 energy Pattern recognition 02 engineering and technology Energy consumption 010501 environmental sciences Fault (power engineering) 01 natural sciences Autoencoder 0202 electrical engineering electronic engineering information engineering Anomaly detection Artificial intelligence Anomaly (physics) business computer 0105 earth and related environmental sciences computer.programming_language |
| Zdroj: | ICTC |
| DOI: | 10.1109/ictc49870.2020.9289226 |
| Popis: | This paper proposes an anomaly detection scheme based on LSTM autoencoder for energy management, which is to prevent anomaly states before they actually occur. When the prognosis of an anomaly state is detected, the anomaly state can be prevented by taking appropriate measures. However, it is difficult to determine normal and anomalous data, since energy consumption varies greatly depending on weather, time, day of the week and season. Thus, this paper proposes an anomaly detection scheme using LSTM autoencoder to detect a data pattern that deviates from the normal data pattern and to determine it as an anomaly state. Experimental results show that this scheme can discriminate anomaly from the observed multivariate data and can be used to prevent fault and incorrect operation in advance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|