Smart Metering System Capable of Anomaly Detection by Bi-directional LSTM Autoencoder

Lee, Sangkeum; Jin, Hojun; Nengroo, Sarvar Hussain; Doh, Yoonmee; Lee, Chungho; Heo, Taewook; Har, Dongsoo

doi:10.1109/icce53296.2022.9730398

Cited by 10 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A decision tree regressor develops a model in the form of a tree structure to estimate data in the future and generate useful continual output by observing the properties of an item. Seamless output denotes the absence of uniform output, i.e., the absence of representation by a discrete, well-known set of values [26]. The number of observations that must have been collected for a tree to contemplate shattering a node into two is known as the minimum sample split parameter.…”

Section: Decision Tree Regressormentioning

confidence: 99%

“…A structure splits until it reaches this value. The level of a decision tree needs to be maintained constantly because a shallower tree is going to possess significant bias along with little variance, whereas a more extensive tree would have high variance and low bias [27,28]. As a result, in our study, we tested using the splitting criterion as well as the maximum depth of the tree to generate a model that is as accurate as possible.…”

Section: Decision Tree Regressormentioning

confidence: 99%

See 1 more Smart Citation

Comparative Analysis Using Multiple Regression Models for Forecasting Photovoltaic Power Generation

Abdullah,

Khanday,

Islam

et al. 2024

Energies

Self Cite

View full text Add to dashboard Cite

Effective machine learning regression models are useful toolsets for managing and planning energy in PV grid-connected systems. Machine learning regression models, however, have been crucial in the analysis, forecasting, and prediction of numerous parameters that support the efficient management of the production and distribution of green energy. This article proposes multiple regression models for power prediction using the Sharda University PV dataset (2022 Edition). The proposed regression model is inspired by a unique data pre-processing technique for forecasting PV power generation. Performance metrics, namely mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), R2-score, and predicted vs. actual value plots, have been used to compare the performance of the different regression. Simulation results show that the multilayer perceptron regressor outperforms the other algorithms, with an RMSE of 17.870 and an R2 score of 0.9377. Feature importance analysis has been performed to determine the most significant features that influence PV power generation.

show abstract

Section: Decision Tree Regressormentioning

confidence: 99%

Section: Decision Tree Regressormentioning

confidence: 99%

Comparative Analysis Using Multiple Regression Models for Forecasting Photovoltaic Power Generation

Abdullah,

Khanday,

Islam

et al. 2024

Energies

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, a RNN-based architecture using Gated Recurrent Units (GRUs) was explored in [40], as online monitor for predicting instability of a power system. An anomaly detection method was also developed in a smart metering system using a bidirectional LSTM-based autoencoder [41]. Additionally, a structural response prediction model of large structures is proposed in [42], using a NARX-based RNN method.…”

Section: Related Workmentioning

confidence: 99%

Gap imputation in related multivariate time series through recurrent neural network-based denoising autoencoder

Alonso,

Morán,

Pérez

et al. 2024

ICA

View full text Add to dashboard Cite

Technological advances in industry have made it possible to install many connected sensors, generating a great amount of observations at high rate. The advent of Industry 4.0 requires analysis capabilities of heterogeneous data in form of related multivariate time series. However, missing data can degrade processing and lead to bias and misunderstandings or even wrong decision-making. In this paper, a recurrent neural network-based denoising autoencoder is proposed for gap imputation in related multivariate time series, i.e., series that exhibit spatio-temporal correlations. The denoising autoencoder (DAE) is able to reproduce input missing data by learning to remove intentionally added gaps, while the recurrent neural network (RNN) captures temporal patterns and relationships among variables. For that reason, different unidirectional (simple RNN, GRU, LSTM) and bidirectional (BiSRNN, BiGRU, BiLSTM) architectures are compared with each other and to state-of-the-art methods using three different datasets in the experiments. The implementation with BiGRU layers outperforms the others, effectively filling gaps with a low reconstruction error. The use of this approach is appropriate for complex scenarios where several variables contain long gaps. However, extreme scenarios with very short gaps in one variable or no available data should be avoided.

show abstract

An empirical evaluation of deep autoencoders for anomaly detection in the electricity consumption of buildings

Azzalini,

Flammini,

Emanuele

et al. 2025

Energy and Buildings

View full text Add to dashboard Cite

Smart Metering System Capable of Anomaly Detection by Bi-directional LSTM Autoencoder

Cited by 10 publications

References 22 publications

Comparative Analysis Using Multiple Regression Models for Forecasting Photovoltaic Power Generation

Comparative Analysis Using Multiple Regression Models for Forecasting Photovoltaic Power Generation

Gap imputation in related multivariate time series through recurrent neural network-based denoising autoencoder

An empirical evaluation of deep autoencoders for anomaly detection in the electricity consumption of buildings

Contact Info

Product

Resources

About