Enhancing Short-Term Load Forecasting Accuracy in High-Volatility Regions Using LSTM-SCN Hybrid Models

Short-Term Load Forecasting (STLF) is essential for the efficient management of power systems, as it improves forecasting accuracy while optimizing power scheduling efficiency. Despite significant recent advancements in STLF models, forecasting accuracy in high-volatility regions remains a key chall...

Full description

Saved in:
Bibliographic Details
Main Authors: Bingbing Tang, Jie Hu, Mei Yang, Chenglong Zhang, Qiang Bai
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/24/11606
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850240283674935296
author Bingbing Tang
Jie Hu
Mei Yang
Chenglong Zhang
Qiang Bai
author_facet Bingbing Tang
Jie Hu
Mei Yang
Chenglong Zhang
Qiang Bai
author_sort Bingbing Tang
collection DOAJ
description Short-Term Load Forecasting (STLF) is essential for the efficient management of power systems, as it improves forecasting accuracy while optimizing power scheduling efficiency. Despite significant recent advancements in STLF models, forecasting accuracy in high-volatility regions remains a key challenge. To address this issue, this paper introduces a hybrid load forecasting model that integrates the Long Short-Term Memory Network (LSTM) with the Stochastic Configuration Network (SCN). We first verify the Universal Approximation Property of SCN through experiments on two regression datasets. Subsequently, we reconstruct the features and input them into the LSTM for feature extraction. These extracted feature vectors are then used as inputs for SCN-based STLF. Finally, we evaluate the performance of the LSTM-SCN model against other baseline models using the Australian Electricity Load dataset. We also select five high-volatility regions in the test set to validate the LSTM-SCN model’s advantages in such scenarios. The results show that the LSTM-SCN model achieved an RMSE of 56.970, MAE of 43.033, and MAPE of 0.492% on the test set. Compared to the next best model, the LSTM-SCN model reduced errors by 6.016, 8.846, and 0.053% for RMSE, MAE, and MAPE, respectively. Additionally, the model consistently outperformed across all five high-volatility regions analyzed. These findings highlight its contribution to improved power system management, particularly in challenging high-volatility scenarios.
format Article
id doaj-art-2e00114698ef42eea486d895a87ebb5d
institution OA Journals
issn 2076-3417
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-2e00114698ef42eea486d895a87ebb5d2025-08-20T02:00:54ZengMDPI AGApplied Sciences2076-34172024-12-0114241160610.3390/app142411606Enhancing Short-Term Load Forecasting Accuracy in High-Volatility Regions Using LSTM-SCN Hybrid ModelsBingbing Tang0Jie Hu1Mei Yang2Chenglong Zhang3Qiang Bai4College of Big Data Statistics, Guizhou University of Finance and Economics, Guiyang 550025, ChinaCollege of Big Data Statistics, Guizhou University of Finance and Economics, Guiyang 550025, ChinaCollege of Big Data Statistics, Guizhou University of Finance and Economics, Guiyang 550025, ChinaSchool of Data Science, The Chinese University of Hong Kong, Shenzhen 518172, ChinaSchool of Mechanical Engineering, Guiyang University, Guiyang 550002, ChinaShort-Term Load Forecasting (STLF) is essential for the efficient management of power systems, as it improves forecasting accuracy while optimizing power scheduling efficiency. Despite significant recent advancements in STLF models, forecasting accuracy in high-volatility regions remains a key challenge. To address this issue, this paper introduces a hybrid load forecasting model that integrates the Long Short-Term Memory Network (LSTM) with the Stochastic Configuration Network (SCN). We first verify the Universal Approximation Property of SCN through experiments on two regression datasets. Subsequently, we reconstruct the features and input them into the LSTM for feature extraction. These extracted feature vectors are then used as inputs for SCN-based STLF. Finally, we evaluate the performance of the LSTM-SCN model against other baseline models using the Australian Electricity Load dataset. We also select five high-volatility regions in the test set to validate the LSTM-SCN model’s advantages in such scenarios. The results show that the LSTM-SCN model achieved an RMSE of 56.970, MAE of 43.033, and MAPE of 0.492% on the test set. Compared to the next best model, the LSTM-SCN model reduced errors by 6.016, 8.846, and 0.053% for RMSE, MAE, and MAPE, respectively. Additionally, the model consistently outperformed across all five high-volatility regions analyzed. These findings highlight its contribution to improved power system management, particularly in challenging high-volatility scenarios.https://www.mdpi.com/2076-3417/14/24/11606Short-Term Load Forecastinghigh-volatility regionsLong Short-Term MemoryStochastic Configuration Networkuniversal approximation property
spellingShingle Bingbing Tang
Jie Hu
Mei Yang
Chenglong Zhang
Qiang Bai
Enhancing Short-Term Load Forecasting Accuracy in High-Volatility Regions Using LSTM-SCN Hybrid Models
Applied Sciences
Short-Term Load Forecasting
high-volatility regions
Long Short-Term Memory
Stochastic Configuration Network
universal approximation property
title Enhancing Short-Term Load Forecasting Accuracy in High-Volatility Regions Using LSTM-SCN Hybrid Models
title_full Enhancing Short-Term Load Forecasting Accuracy in High-Volatility Regions Using LSTM-SCN Hybrid Models
title_fullStr Enhancing Short-Term Load Forecasting Accuracy in High-Volatility Regions Using LSTM-SCN Hybrid Models
title_full_unstemmed Enhancing Short-Term Load Forecasting Accuracy in High-Volatility Regions Using LSTM-SCN Hybrid Models
title_short Enhancing Short-Term Load Forecasting Accuracy in High-Volatility Regions Using LSTM-SCN Hybrid Models
title_sort enhancing short term load forecasting accuracy in high volatility regions using lstm scn hybrid models
topic Short-Term Load Forecasting
high-volatility regions
Long Short-Term Memory
Stochastic Configuration Network
universal approximation property
url https://www.mdpi.com/2076-3417/14/24/11606
work_keys_str_mv AT bingbingtang enhancingshorttermloadforecastingaccuracyinhighvolatilityregionsusinglstmscnhybridmodels
AT jiehu enhancingshorttermloadforecastingaccuracyinhighvolatilityregionsusinglstmscnhybridmodels
AT meiyang enhancingshorttermloadforecastingaccuracyinhighvolatilityregionsusinglstmscnhybridmodels
AT chenglongzhang enhancingshorttermloadforecastingaccuracyinhighvolatilityregionsusinglstmscnhybridmodels
AT qiangbai enhancingshorttermloadforecastingaccuracyinhighvolatilityregionsusinglstmscnhybridmodels