Recurrent Neural Network-Based Autoencoder for Problems of Automatic Time Series Analysis at Power Facilities
-
Published:2023-05
Issue:2(58)
Volume:
Page:61-71
-
ISSN:1857-0070
-
Container-title:Problems of the Regional Energetics
-
language:
-
Short-container-title:PRE
Author:
Matrenin P.V.,Khalyasmaa A.I.,Potachits Y.V.
Abstract
Digitalization of the energy sector leads to an increase in the volume and rate of data collection. A primary barrier to the proper management of the technological data is the lack of data labeling corresponding to emergency modes, power equipment technical state, etc. Thus, despite the large amount of data, there is a shortage of labeled data suitable for training, validating and testing the machine learning models. Labeling by an expert takes too much time, so there is an actual task to automatically identify data fragments that are potentially of interest. The aim of the work is to develop an algorithm for prioritizing the fragments of the time series using the compact recurrent autoencoder. To achieve the goal, a neural network architecture was developed based on recurrent encoding and decoding cells, capable of unsupervised learning. The model was tested on two data sets: a synthetic sinusoidal signal with missing values and electric current measurements with thermal limit deviations. The substantial results of the work are the compact architecture of the autocoding model and the high interpretability of the output. The most significant achievements of the study are both the autocoding neural network model, which does not require initial assumption about the type of deviations, and the proposed algorithm for prioritizing the data fragments. The significance of the results is prooved by the reduction of the time for analyzing and labeling large data arrays with technological parameters of the electrical networks, which allows using these data for training, validating and testing.
Publisher
Technical University of Moldova
Subject
Energy (miscellaneous),Energy Engineering and Power Technology,Fuel Technology,Renewable Energy, Sustainability and the Environment
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Using Neural Network-Based Time Series Analysis in Wireless Sensor Networks;2024 2nd International Conference on Artificial Intelligence and Machine Learning Applications Theme: Healthcare and Internet of Things (AIMLA);2024-03-15