Short-term load forecasting based on feature mining and deep learning of big data of user electricity consumption
This study proposes a short-term load prediction method of a bidirectional long short-term memory network based on feature mining of the power consumption big data in combination with the attention mechanism (AT) of Bayesian optimization to address the problems that a considerable amount of feature...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2023-12-01
|
| Series: | AIP Advances |
| Online Access: | http://dx.doi.org/10.1063/5.0176239 |
| _version_ | 1797367046636306432 |
|---|---|
| author | Ming Wen Zongchao Yu Wenying Li Shuchen Luo Yuan Zhong Chen Changqing |
| author_facet | Ming Wen Zongchao Yu Wenying Li Shuchen Luo Yuan Zhong Chen Changqing |
| author_sort | Ming Wen |
| collection | DOAJ |
| description | This study proposes a short-term load prediction method of a bidirectional long short-term memory network based on feature mining of the power consumption big data in combination with the attention mechanism (AT) of Bayesian optimization to address the problems that a considerable amount of feature factors exist and the feature relationship is obscured in the historical power consumption big data. The method comprehensively considers the global features of the power consumption data in space and the local features in time. First, the Cen-CK-means clustering method is used to cluster the electricity consumption data of users, and the statistical, combination, and time category characteristics are extracted according to the meteorological factors related to load over multiple time scales. Second, the Bayesian and bidirectional long and short memory networks are combined to extract the temporal and spatial characteristics of the load data itself. Meanwhile, the AT is introduced to automatically assign the corresponding weights to the hidden layer state of the bidirectional long and short memory. This task is carried out to distinguish the importance of the different time load series, which can effectively reduce the loss of historical information and highlight information about key historical time points. Finally, taking the first type of load as an example, compared with the SVP, RBPNN, BiLSTM, and BO-BiLSTM algorithms, the MAPE index is reduced by 1.05%, 1.75%, 0.52%, and 0.26%, respectively. RMSE decreased by 186.61, 154.93, 91.88, and 15.76 MW, respectively, while R2 increased by 0.04, 0.07, 0.03, and 0.03, respectively. In the one-week forecast time, MAPE index decreased by 1.97%, 2.44%, 1.21%, and 0.6%, respectively; RMSE decreased by 271.18, 305.7, 183.13, and 97.91 MW, respectively; and R2 increased by 0.12, 0.08, 0.04, and 0.03, respectively. |
| first_indexed | 2024-03-08T17:12:20Z |
| format | Article |
| id | doaj.art-e2e1353b0ada4733bb463cfbb3f2a90c |
| institution | Directory Open Access Journal |
| issn | 2158-3226 |
| language | English |
| last_indexed | 2024-03-08T17:12:20Z |
| publishDate | 2023-12-01 |
| publisher | AIP Publishing LLC |
| record_format | Article |
| series | AIP Advances |
| spelling | doaj.art-e2e1353b0ada4733bb463cfbb3f2a90c2024-01-03T19:51:07ZengAIP Publishing LLCAIP Advances2158-32262023-12-011312125315125315-1410.1063/5.0176239Short-term load forecasting based on feature mining and deep learning of big data of user electricity consumptionMing Wen0Zongchao Yu1Wenying Li2Shuchen Luo3Yuan Zhong4Chen Changqing5Economic Research Institute, Hunan Key Laboratory of Energy Internet Supply-demand and Operation, State Grid Hunan Electric Power Company, Changsha 410004, ChinaEconomic Research Institute, Hunan Key Laboratory of Energy Internet Supply-demand and Operation, State Grid Hunan Electric Power Company, Changsha 410004, ChinaEconomic Research Institute, Hunan Key Laboratory of Energy Internet Supply-demand and Operation, State Grid Hunan Electric Power Company, Changsha 410004, ChinaEconomic Research Institute, Hunan Key Laboratory of Energy Internet Supply-demand and Operation, State Grid Hunan Electric Power Company, Changsha 410004, ChinaEconomic Research Institute, Hunan Key Laboratory of Energy Internet Supply-demand and Operation, State Grid Hunan Electric Power Company, Changsha 410004, ChinaKey Laboratory of Smart City Energy Sensing and Edge Computing of Hunan Province, Hunan City University, Yiyang 413000, ChinaThis study proposes a short-term load prediction method of a bidirectional long short-term memory network based on feature mining of the power consumption big data in combination with the attention mechanism (AT) of Bayesian optimization to address the problems that a considerable amount of feature factors exist and the feature relationship is obscured in the historical power consumption big data. The method comprehensively considers the global features of the power consumption data in space and the local features in time. First, the Cen-CK-means clustering method is used to cluster the electricity consumption data of users, and the statistical, combination, and time category characteristics are extracted according to the meteorological factors related to load over multiple time scales. Second, the Bayesian and bidirectional long and short memory networks are combined to extract the temporal and spatial characteristics of the load data itself. Meanwhile, the AT is introduced to automatically assign the corresponding weights to the hidden layer state of the bidirectional long and short memory. This task is carried out to distinguish the importance of the different time load series, which can effectively reduce the loss of historical information and highlight information about key historical time points. Finally, taking the first type of load as an example, compared with the SVP, RBPNN, BiLSTM, and BO-BiLSTM algorithms, the MAPE index is reduced by 1.05%, 1.75%, 0.52%, and 0.26%, respectively. RMSE decreased by 186.61, 154.93, 91.88, and 15.76 MW, respectively, while R2 increased by 0.04, 0.07, 0.03, and 0.03, respectively. In the one-week forecast time, MAPE index decreased by 1.97%, 2.44%, 1.21%, and 0.6%, respectively; RMSE decreased by 271.18, 305.7, 183.13, and 97.91 MW, respectively; and R2 increased by 0.12, 0.08, 0.04, and 0.03, respectively.http://dx.doi.org/10.1063/5.0176239 |
| spellingShingle | Ming Wen Zongchao Yu Wenying Li Shuchen Luo Yuan Zhong Chen Changqing Short-term load forecasting based on feature mining and deep learning of big data of user electricity consumption AIP Advances |
| title | Short-term load forecasting based on feature mining and deep learning of big data of user electricity consumption |
| title_full | Short-term load forecasting based on feature mining and deep learning of big data of user electricity consumption |
| title_fullStr | Short-term load forecasting based on feature mining and deep learning of big data of user electricity consumption |
| title_full_unstemmed | Short-term load forecasting based on feature mining and deep learning of big data of user electricity consumption |
| title_short | Short-term load forecasting based on feature mining and deep learning of big data of user electricity consumption |
| title_sort | short term load forecasting based on feature mining and deep learning of big data of user electricity consumption |
| url | http://dx.doi.org/10.1063/5.0176239 |
| work_keys_str_mv | AT mingwen shorttermloadforecastingbasedonfeaturemininganddeeplearningofbigdataofuserelectricityconsumption AT zongchaoyu shorttermloadforecastingbasedonfeaturemininganddeeplearningofbigdataofuserelectricityconsumption AT wenyingli shorttermloadforecastingbasedonfeaturemininganddeeplearningofbigdataofuserelectricityconsumption AT shuchenluo shorttermloadforecastingbasedonfeaturemininganddeeplearningofbigdataofuserelectricityconsumption AT yuanzhong shorttermloadforecastingbasedonfeaturemininganddeeplearningofbigdataofuserelectricityconsumption AT chenchangqing shorttermloadforecastingbasedonfeaturemininganddeeplearningofbigdataofuserelectricityconsumption |