Next Article in Journal
A Review on Electrical Impedance Tomography Spectroscopy
Previous Article in Journal
Pattern Synthesis of Linear Antenna Array Using Improved Differential Evolution Algorithm with SPS Framework
Article

A Multitiered Solution for Anomaly Detection in Edge Computing for Smart Meters

1
Computer Science and Information Engineering, National Chung Cheng University, No. 168, Sec. 1, University Rd., Minhsiung, Chiayi 62102, Taiwan
2
Faculty of Electronics and Computer Engineering, Satya Wacana Christian University, Jalan Diponegoro 52-60, Salatiga 50711, Indonesia
*
Author to whom correspondence should be addressed.
Sensors 2020, 20(18), 5159; https://doi.org/10.3390/s20185159
Received: 22 July 2020 / Revised: 17 August 2020 / Accepted: 25 August 2020 / Published: 10 September 2020
(This article belongs to the Section Sensor Networks)
In systems connected to smart grids, smart meters with fast and efficient responses are very helpful in detecting anomalies in realtime. However, sending data with a frequency of a minute or less is not normal with today’s technology because of the bottleneck of the communication network and storage media. Because mitigation cannot be done in realtime, we propose prediction techniques using Deep Neural Network (DNN), Support Vector Regression (SVR), and k-Nearest Neighbors (KNN). In addition to these techniques, the prediction timestep is chosen per day and wrapped in sliding windows, and clustering using Kmeans and intersection Kmeans and HDBSCAN is also evaluated. The predictive ability applied here is to predict whether anomalies in electricity usage will occur in the next few weeks. The aim is to give the user time to check their usage and from the utility side, whether it is necessary to prepare a sufficient supply. We also propose the latency reduction to counter higher latency as in the traditional centralized system by adding layer Edge Meter Data Management System (MDMS) and Cloud-MDMS as the inference and training model. Based on the experiments when running in the Raspberry Pi, the best solution is choosing DNN that has the shortest latency 1.25 ms, 159 kB persistent file size, and at 128 timesteps. View Full-Text
Keywords: anomaly detection; LSTM; SVR; k-NN; edge; fog; cloud; smart meter; imbalanced; K-means; HDBSCAN; AMI; DNN anomaly detection; LSTM; SVR; k-NN; edge; fog; cloud; smart meter; imbalanced; K-means; HDBSCAN; AMI; DNN
Show Figures

Figure 1

MDPI and ACS Style

Utomo, D.; Hsiung, P.-A. A Multitiered Solution for Anomaly Detection in Edge Computing for Smart Meters. Sensors 2020, 20, 5159. https://doi.org/10.3390/s20185159

AMA Style

Utomo D, Hsiung P-A. A Multitiered Solution for Anomaly Detection in Edge Computing for Smart Meters. Sensors. 2020; 20(18):5159. https://doi.org/10.3390/s20185159

Chicago/Turabian Style

Utomo, Darmawan, and Pao-Ann Hsiung. 2020. "A Multitiered Solution for Anomaly Detection in Edge Computing for Smart Meters" Sensors 20, no. 18: 5159. https://doi.org/10.3390/s20185159

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop