Unsupervised Anomaly Detection of Shipboard Electrical Power Consumption Through GRU Autoencoder Model
- 17 June 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
Anomaly detection (AD) in modern electrical microgrids is critical for ensuring reliable and safe operation as well as in improving the operational and maintenance efficiency of the infrastructure. This is particularly true for on-board microgrids, given their inherent electrical weakness and predominantly isolated operation. This paper proposes a machine learning-based approach for performing anomaly detection (AD) in electrical power consumption of a large passenger ship. The developed AD method relies on a gate recurrent unit (GRU) autoencoder (AE) model trained and validated with a multivariate electrical power time series collected from a real-world vessel. The proposed GRU AE approach is compared with different AE models, training and testing all models on an unsupervised context, and their performance is evaluated using various metrics suitable for such an unsupervised context.Keywords
Funding Information
- MUR
This publication has 28 references indexed in Scilit:
- Day-ahead forecasting of residential electric power consumption for energy management using Long Short-Term Memory encoder–decoder modelMathematics and Computers in Simulation, 2023
- Artificial intelligence based anomaly detection of energy consumption in buildings: A review, current trends and new perspectivesApplied Energy, 2021
- Fault diagnosis of shipboard medium-voltage DC power system based on machine learningInternational Journal of Electrical Power & Energy Systems, 2021
- A Novel Approach for Detecting Anomalous Energy Consumption Based on Micro-Moments and Deep Neural NetworksCognitive Computation, 2020
- Spacecraft Anomaly Detection via Transformer Reconstruction Error2020
- MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks2019
- Unsupervised anomaly detection based on clustering methods and sensor data on a marine diesel engineJournal of Marine Engineering & Technology, 2019
- Unsupervised real-time anomaly detection for streaming dataNeurocomputing, 2017
- Development of prediction models for next-day building energy consumption and peak power demand using data mining techniquesApplied Energy, 2014
- Real-time detection of anomalous power consumptionRenewable and Sustainable Energy Reviews, 2014