Time Series Data Augmentation for Energy Consumption Data Based on Improved TimeGAN

Predicting the time series energy consumption data of manufacturing processes can optimize energy management efficiency and reduce maintenance costs for enterprises. Using deep learning algorithms to establish prediction models for sensor data is an effective approach; however, the performance of th...

Full description

Saved in:
Bibliographic Details
Main Authors: Peihao Tang, Zhen Li, Xuanlin Wang, Xueping Liu, Peng Mou
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/2/493
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832587524754636800
author Peihao Tang
Zhen Li
Xuanlin Wang
Xueping Liu
Peng Mou
author_facet Peihao Tang
Zhen Li
Xuanlin Wang
Xueping Liu
Peng Mou
author_sort Peihao Tang
collection DOAJ
description Predicting the time series energy consumption data of manufacturing processes can optimize energy management efficiency and reduce maintenance costs for enterprises. Using deep learning algorithms to establish prediction models for sensor data is an effective approach; however, the performance of these models is significantly influenced by the quantity and quality of the training data. In real production environments, the amount of time series data that can be collected during the manufacturing process is limited, which can lead to a decline in model performance. In this paper, we use an improved TimeGAN model for the augmentation of energy consumption data, which incorporates a multi-head self-attention mechanism layer into the recovery model to enhance prediction accuracy. A hybrid CNN-GRU model is used to predict the energy consumption data from the operational processes of manufacturing equipment. After data augmentation, the prediction model exhibits significant reductions in RMSE and MAE along with an increase in the R<sup>2</sup> value. The prediction accuracy of the model is maximized when the amount of generated synthetic data is approximately twice that of the original data.
format Article
id doaj-art-c42407788a7344c6bfc60872c520d224
institution Kabale University
issn 1424-8220
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-c42407788a7344c6bfc60872c520d2242025-01-24T13:49:07ZengMDPI AGSensors1424-82202025-01-0125249310.3390/s25020493Time Series Data Augmentation for Energy Consumption Data Based on Improved TimeGANPeihao Tang0Zhen Li1Xuanlin Wang2Xueping Liu3Peng Mou4Division of Advanced Manufacturing, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaDivision of Advanced Manufacturing, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaDivision of Advanced Manufacturing, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaDivision of Advanced Manufacturing, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaDepartment of Mechanical Engineering, Tsinghua University, Beijing 100084, ChinaPredicting the time series energy consumption data of manufacturing processes can optimize energy management efficiency and reduce maintenance costs for enterprises. Using deep learning algorithms to establish prediction models for sensor data is an effective approach; however, the performance of these models is significantly influenced by the quantity and quality of the training data. In real production environments, the amount of time series data that can be collected during the manufacturing process is limited, which can lead to a decline in model performance. In this paper, we use an improved TimeGAN model for the augmentation of energy consumption data, which incorporates a multi-head self-attention mechanism layer into the recovery model to enhance prediction accuracy. A hybrid CNN-GRU model is used to predict the energy consumption data from the operational processes of manufacturing equipment. After data augmentation, the prediction model exhibits significant reductions in RMSE and MAE along with an increase in the R<sup>2</sup> value. The prediction accuracy of the model is maximized when the amount of generated synthetic data is approximately twice that of the original data.https://www.mdpi.com/1424-8220/25/2/493data augmentationTimeGANdeep learningtime series
spellingShingle Peihao Tang
Zhen Li
Xuanlin Wang
Xueping Liu
Peng Mou
Time Series Data Augmentation for Energy Consumption Data Based on Improved TimeGAN
Sensors
data augmentation
TimeGAN
deep learning
time series
title Time Series Data Augmentation for Energy Consumption Data Based on Improved TimeGAN
title_full Time Series Data Augmentation for Energy Consumption Data Based on Improved TimeGAN
title_fullStr Time Series Data Augmentation for Energy Consumption Data Based on Improved TimeGAN
title_full_unstemmed Time Series Data Augmentation for Energy Consumption Data Based on Improved TimeGAN
title_short Time Series Data Augmentation for Energy Consumption Data Based on Improved TimeGAN
title_sort time series data augmentation for energy consumption data based on improved timegan
topic data augmentation
TimeGAN
deep learning
time series
url https://www.mdpi.com/1424-8220/25/2/493
work_keys_str_mv AT peihaotang timeseriesdataaugmentationforenergyconsumptiondatabasedonimprovedtimegan
AT zhenli timeseriesdataaugmentationforenergyconsumptiondatabasedonimprovedtimegan
AT xuanlinwang timeseriesdataaugmentationforenergyconsumptiondatabasedonimprovedtimegan
AT xuepingliu timeseriesdataaugmentationforenergyconsumptiondatabasedonimprovedtimegan
AT pengmou timeseriesdataaugmentationforenergyconsumptiondatabasedonimprovedtimegan