Training improvement methods of ANN trajectory predictors in power systems

Abstract This paper proposes training improvement methods of artificial neural networks (ANN) trajectory predictors. First, a dynamic power system time‐series trajectory is split into several different segments to simplify the original ANN training problem. Moreover, the time‐derivative of the traje...

Full description

Saved in:
Bibliographic Details
Main Author: Sangwon Kim
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:IET Generation, Transmission & Distribution
Subjects:
Online Access:https://doi.org/10.1049/gtd2.13339
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849714441374924800
author Sangwon Kim
author_facet Sangwon Kim
author_sort Sangwon Kim
collection DOAJ
description Abstract This paper proposes training improvement methods of artificial neural networks (ANN) trajectory predictors. First, a dynamic power system time‐series trajectory is split into several different segments to simplify the original ANN training problem. Moreover, the time‐derivative of the trajectory is included to obtain an augmented loss function. Compared to previous studies which mainly focused on increasing the prediction accuracy, the aim of these novel techniques is to reduce the computational burden where the ANN output performance is still acceptable. The effectiveness of the developed methods is validated based on the WSCC three‐machine nine‐bus and IEEE 39‐bus system models. The mean absolute error (MAE) and trajectory prediction results are analysed, in which the numbers of neurons, hidden layers, and training epochs are constrained during the ANN training process. Rotor‐angle difference between generators and the system frequency are investigated as the dynamic trajectories of the power system models. The approaches are revealed to be effective when the ANN architecture and epochs are constrained. The MAE results can be reduced by up to 65% in the power system models depending on the ANN hyperparameters and training epochs. The ANN training results can better reflect the original trajectory as well.
format Article
id doaj-art-d94cd4bdb69746d8be72d3e25fe12861
institution DOAJ
issn 1751-8687
1751-8695
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series IET Generation, Transmission & Distribution
spelling doaj-art-d94cd4bdb69746d8be72d3e25fe128612025-08-20T03:13:42ZengWileyIET Generation, Transmission & Distribution1751-86871751-86952024-12-0118244105411510.1049/gtd2.13339Training improvement methods of ANN trajectory predictors in power systemsSangwon Kim0School of Electrical Engineering University of Ulsan Ulsan Republic of KoreaAbstract This paper proposes training improvement methods of artificial neural networks (ANN) trajectory predictors. First, a dynamic power system time‐series trajectory is split into several different segments to simplify the original ANN training problem. Moreover, the time‐derivative of the trajectory is included to obtain an augmented loss function. Compared to previous studies which mainly focused on increasing the prediction accuracy, the aim of these novel techniques is to reduce the computational burden where the ANN output performance is still acceptable. The effectiveness of the developed methods is validated based on the WSCC three‐machine nine‐bus and IEEE 39‐bus system models. The mean absolute error (MAE) and trajectory prediction results are analysed, in which the numbers of neurons, hidden layers, and training epochs are constrained during the ANN training process. Rotor‐angle difference between generators and the system frequency are investigated as the dynamic trajectories of the power system models. The approaches are revealed to be effective when the ANN architecture and epochs are constrained. The MAE results can be reduced by up to 65% in the power system models depending on the ANN hyperparameters and training epochs. The ANN training results can better reflect the original trajectory as well.https://doi.org/10.1049/gtd2.13339neural netspower system measurement
spellingShingle Sangwon Kim
Training improvement methods of ANN trajectory predictors in power systems
IET Generation, Transmission & Distribution
neural nets
power system measurement
title Training improvement methods of ANN trajectory predictors in power systems
title_full Training improvement methods of ANN trajectory predictors in power systems
title_fullStr Training improvement methods of ANN trajectory predictors in power systems
title_full_unstemmed Training improvement methods of ANN trajectory predictors in power systems
title_short Training improvement methods of ANN trajectory predictors in power systems
title_sort training improvement methods of ann trajectory predictors in power systems
topic neural nets
power system measurement
url https://doi.org/10.1049/gtd2.13339
work_keys_str_mv AT sangwonkim trainingimprovementmethodsofanntrajectorypredictorsinpowersystems