Demand-Side Electricity Load Forecasting Based on Time-Series Decomposition Combined with Kernel Extreme Learning Machine Improved by Sparrow Algorithm
With the rapid development of new power systems, power usage stations are becoming more diverse and complex. Fine-grained management of demand-side power load has become increasingly crucial. To address the accurate load forecasting needs for various demand-side power consumption types and provide d...
Published in: | Energies |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2023
|
Subjects: | |
Online Access: | https://doi.org/10.3390/en16237714 https://doaj.org/article/36212f35d60f48aabb1b71c51d36f786 |
id |
ftdoajarticles:oai:doaj.org/article:36212f35d60f48aabb1b71c51d36f786 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:36212f35d60f48aabb1b71c51d36f786 2024-01-07T09:45:30+01:00 Demand-Side Electricity Load Forecasting Based on Time-Series Decomposition Combined with Kernel Extreme Learning Machine Improved by Sparrow Algorithm Liyuan Sun Yuang Lin Nan Pan Qiang Fu Liuyong Chen Junwei Yang 2023-11-01T00:00:00Z https://doi.org/10.3390/en16237714 https://doaj.org/article/36212f35d60f48aabb1b71c51d36f786 EN eng MDPI AG https://www.mdpi.com/1996-1073/16/23/7714 https://doaj.org/toc/1996-1073 doi:10.3390/en16237714 1996-1073 https://doaj.org/article/36212f35d60f48aabb1b71c51d36f786 Energies, Vol 16, Iss 23, p 7714 (2023) load forecasting variational mode decomposition northern goshawk optimization algorithm improved kernel extreme learning machine power system load management Technology T article 2023 ftdoajarticles https://doi.org/10.3390/en16237714 2023-12-10T01:36:48Z With the rapid development of new power systems, power usage stations are becoming more diverse and complex. Fine-grained management of demand-side power load has become increasingly crucial. To address the accurate load forecasting needs for various demand-side power consumption types and provide data support for load management in diverse stations, this study proposes a load sequence noise reduction method. Initially, wavelet noise reduction is performed on the multiple types of load sequences collected by the power system. Subsequently, the northern goshawk optimization is employed to optimize the parameters of variational mode decomposition, ensuring the selection of the most suitable modal decomposition parameters for different load sequences. Next, the SSA–KELM model is employed to independently predict each sub-modal component. The predicted values for each sub-modal component are then aggregated to yield short-term load prediction results. The proposed load forecasting method has been verified using actual data collected from various types of power terminals. A comparison with popular load forecasting methods demonstrates the proposed method’s higher prediction accuracy and versatility. The average prediction results of load data in industrial stations can reach RMSE = 0.0098, MAE = 0.0078, MAPE = 1.3897%, and R 2 = 0.9949. This method can be effectively applied to short-term load forecasting in multiple types of power stations, providing a reliable basis for accurate demand-side power load management and decision-making. Article in Journal/Newspaper Northern Goshawk Directory of Open Access Journals: DOAJ Articles Energies 16 23 7714 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
load forecasting variational mode decomposition northern goshawk optimization algorithm improved kernel extreme learning machine power system load management Technology T |
spellingShingle |
load forecasting variational mode decomposition northern goshawk optimization algorithm improved kernel extreme learning machine power system load management Technology T Liyuan Sun Yuang Lin Nan Pan Qiang Fu Liuyong Chen Junwei Yang Demand-Side Electricity Load Forecasting Based on Time-Series Decomposition Combined with Kernel Extreme Learning Machine Improved by Sparrow Algorithm |
topic_facet |
load forecasting variational mode decomposition northern goshawk optimization algorithm improved kernel extreme learning machine power system load management Technology T |
description |
With the rapid development of new power systems, power usage stations are becoming more diverse and complex. Fine-grained management of demand-side power load has become increasingly crucial. To address the accurate load forecasting needs for various demand-side power consumption types and provide data support for load management in diverse stations, this study proposes a load sequence noise reduction method. Initially, wavelet noise reduction is performed on the multiple types of load sequences collected by the power system. Subsequently, the northern goshawk optimization is employed to optimize the parameters of variational mode decomposition, ensuring the selection of the most suitable modal decomposition parameters for different load sequences. Next, the SSA–KELM model is employed to independently predict each sub-modal component. The predicted values for each sub-modal component are then aggregated to yield short-term load prediction results. The proposed load forecasting method has been verified using actual data collected from various types of power terminals. A comparison with popular load forecasting methods demonstrates the proposed method’s higher prediction accuracy and versatility. The average prediction results of load data in industrial stations can reach RMSE = 0.0098, MAE = 0.0078, MAPE = 1.3897%, and R 2 = 0.9949. This method can be effectively applied to short-term load forecasting in multiple types of power stations, providing a reliable basis for accurate demand-side power load management and decision-making. |
format |
Article in Journal/Newspaper |
author |
Liyuan Sun Yuang Lin Nan Pan Qiang Fu Liuyong Chen Junwei Yang |
author_facet |
Liyuan Sun Yuang Lin Nan Pan Qiang Fu Liuyong Chen Junwei Yang |
author_sort |
Liyuan Sun |
title |
Demand-Side Electricity Load Forecasting Based on Time-Series Decomposition Combined with Kernel Extreme Learning Machine Improved by Sparrow Algorithm |
title_short |
Demand-Side Electricity Load Forecasting Based on Time-Series Decomposition Combined with Kernel Extreme Learning Machine Improved by Sparrow Algorithm |
title_full |
Demand-Side Electricity Load Forecasting Based on Time-Series Decomposition Combined with Kernel Extreme Learning Machine Improved by Sparrow Algorithm |
title_fullStr |
Demand-Side Electricity Load Forecasting Based on Time-Series Decomposition Combined with Kernel Extreme Learning Machine Improved by Sparrow Algorithm |
title_full_unstemmed |
Demand-Side Electricity Load Forecasting Based on Time-Series Decomposition Combined with Kernel Extreme Learning Machine Improved by Sparrow Algorithm |
title_sort |
demand-side electricity load forecasting based on time-series decomposition combined with kernel extreme learning machine improved by sparrow algorithm |
publisher |
MDPI AG |
publishDate |
2023 |
url |
https://doi.org/10.3390/en16237714 https://doaj.org/article/36212f35d60f48aabb1b71c51d36f786 |
genre |
Northern Goshawk |
genre_facet |
Northern Goshawk |
op_source |
Energies, Vol 16, Iss 23, p 7714 (2023) |
op_relation |
https://www.mdpi.com/1996-1073/16/23/7714 https://doaj.org/toc/1996-1073 doi:10.3390/en16237714 1996-1073 https://doaj.org/article/36212f35d60f48aabb1b71c51d36f786 |
op_doi |
https://doi.org/10.3390/en16237714 |
container_title |
Energies |
container_volume |
16 |
container_issue |
23 |
container_start_page |
7714 |
_version_ |
1787427042507096064 |