A Method for Anomaly Prediction in Power Consumption using Long Short-Term Memory and Negative Selection
| Autor: | Bruno W. S. Arruda, R. S. Freire, Edmar C. Gurjao, Ivana Soares Guarany, Andresso da Silva |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
business.industry 020209 energy Detector Real-time computing 020206 networking & telecommunications 02 engineering and technology Negative selection Memory management 0202 electrical engineering electronic engineering information engineering Anomaly detection Electricity Anomaly (physics) business Efficient energy use |
| Zdroj: | ISCAS |
| DOI: | 10.1109/iscas.2019.8702152 |
| Popis: | To identify and predict anomalous power consumption, this paper proposes a method based on Long Short-Term Memory (LSTM) and Negative Selection technologies that anticipates the occurrence of anomalies in power consumption, and to provide useful information for energy efficiency. Using the proposed method it is possible to anticipate the occurrence of anomalies in power consumption. When applied to the power consumption recorded during 20 weeks of a building the method yielded promising results. Finally, the effectiveness and advantages of this method is demonstrated which it could be directly used for real-time electricity monitoring and anomaly prediction. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|