Learning model combined with data clustering and dimensionality reduction for short-term electricity load forecasting
Abstract Electric load forecasting is crucial in the planning and operating electric power companies. It has evolved from statistical methods to artificial intelligence-based techniques that use machine learning models. In this study, we investigate short-term load forecasting (STLF) for large-scale...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-86982-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571808485736448 |
|---|---|
| author | Hyun-Jung Bae Jong-Seong Park Ji-hyeok Choi Hyuk-Yoon Kwon |
| author_facet | Hyun-Jung Bae Jong-Seong Park Ji-hyeok Choi Hyuk-Yoon Kwon |
| author_sort | Hyun-Jung Bae |
| collection | DOAJ |
| description | Abstract Electric load forecasting is crucial in the planning and operating electric power companies. It has evolved from statistical methods to artificial intelligence-based techniques that use machine learning models. In this study, we investigate short-term load forecasting (STLF) for large-scale electricity usage datasets. We propose a new prediction model for STLF that combines data clustering and dimensionality reduction schemes to handle large-scale electricity usage data effectively. Here, we adapt k-means clustering for data clustering, kernel principal component analysis (kernel PCA), universal manifold approximation and projection (UMAP), and t-stochastic nearest neighbor (t-SNE) for dimensionality reduction. To verify the effectiveness of the proposed model, we extensively apply it to neural network-based models. We compare and analyze the performance of the proposed model with the comparisons using actual electricity usage data for 4710 households. Experimental results demonstrate that data clustering with dimensionality reduction can improve the performance of baseline models. As a result, the prediction accuracy of the proposed method outperforms those of the existing methods by 1.01–1.76 times for summer data and by 1.03–1.36 times for winter data in terms of mean absolute percentage error (MAPE). |
| format | Article |
| id | doaj-art-a0f6cb8dde5e46bebf63ddb2a9cf419f |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-a0f6cb8dde5e46bebf63ddb2a9cf419f2025-02-02T12:19:21ZengNature PortfolioScientific Reports2045-23222025-01-0115111710.1038/s41598-025-86982-0Learning model combined with data clustering and dimensionality reduction for short-term electricity load forecastingHyun-Jung Bae0Jong-Seong Park1Ji-hyeok Choi2Hyuk-Yoon Kwon3Graduate School of Data Science, Seoul National University of Science and TechnologyGraduate School of Data Science, Seoul National University of Science and TechnologyDepartment of Industrial Engineering, Seoul National University of Science and TechnologyDepartment of Industrial Engineering/Graduate School of Data Science/Research Center for Electrical and Information Science, Seoul National University of Science and TechnologyAbstract Electric load forecasting is crucial in the planning and operating electric power companies. It has evolved from statistical methods to artificial intelligence-based techniques that use machine learning models. In this study, we investigate short-term load forecasting (STLF) for large-scale electricity usage datasets. We propose a new prediction model for STLF that combines data clustering and dimensionality reduction schemes to handle large-scale electricity usage data effectively. Here, we adapt k-means clustering for data clustering, kernel principal component analysis (kernel PCA), universal manifold approximation and projection (UMAP), and t-stochastic nearest neighbor (t-SNE) for dimensionality reduction. To verify the effectiveness of the proposed model, we extensively apply it to neural network-based models. We compare and analyze the performance of the proposed model with the comparisons using actual electricity usage data for 4710 households. Experimental results demonstrate that data clustering with dimensionality reduction can improve the performance of baseline models. As a result, the prediction accuracy of the proposed method outperforms those of the existing methods by 1.01–1.76 times for summer data and by 1.03–1.36 times for winter data in terms of mean absolute percentage error (MAPE).https://doi.org/10.1038/s41598-025-86982-0 |
| spellingShingle | Hyun-Jung Bae Jong-Seong Park Ji-hyeok Choi Hyuk-Yoon Kwon Learning model combined with data clustering and dimensionality reduction for short-term electricity load forecasting Scientific Reports |
| title | Learning model combined with data clustering and dimensionality reduction for short-term electricity load forecasting |
| title_full | Learning model combined with data clustering and dimensionality reduction for short-term electricity load forecasting |
| title_fullStr | Learning model combined with data clustering and dimensionality reduction for short-term electricity load forecasting |
| title_full_unstemmed | Learning model combined with data clustering and dimensionality reduction for short-term electricity load forecasting |
| title_short | Learning model combined with data clustering and dimensionality reduction for short-term electricity load forecasting |
| title_sort | learning model combined with data clustering and dimensionality reduction for short term electricity load forecasting |
| url | https://doi.org/10.1038/s41598-025-86982-0 |
| work_keys_str_mv | AT hyunjungbae learningmodelcombinedwithdataclusteringanddimensionalityreductionforshorttermelectricityloadforecasting AT jongseongpark learningmodelcombinedwithdataclusteringanddimensionalityreductionforshorttermelectricityloadforecasting AT jihyeokchoi learningmodelcombinedwithdataclusteringanddimensionalityreductionforshorttermelectricityloadforecasting AT hyukyoonkwon learningmodelcombinedwithdataclusteringanddimensionalityreductionforshorttermelectricityloadforecasting |