Short-Term Load Forecasting Based on the CEEMDAN-Sample Entropy-BPNN-Transformer
Aiming at the problem that power load data are stochastic and that it is difficult to obtain accurate forecasting results by a single algorithm, in this paper, a combined forecasting method for short-term power load was proposed based on the Complete Ensemble Empirical Mode Decomposition with Adapti...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/10/3659 |
| _version_ | 1827669186700115968 |
|---|---|
| author | Shichao Huang Jing Zhang Yu He Xiaofan Fu Luqin Fan Gang Yao Yongjun Wen |
| author_facet | Shichao Huang Jing Zhang Yu He Xiaofan Fu Luqin Fan Gang Yao Yongjun Wen |
| author_sort | Shichao Huang |
| collection | DOAJ |
| description | Aiming at the problem that power load data are stochastic and that it is difficult to obtain accurate forecasting results by a single algorithm, in this paper, a combined forecasting method for short-term power load was proposed based on the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN)-sample entropy (SE), the BP neural network (BPNN), and the Transformer model. Firstly, the power load data were decomposed into several power load subsequences with obvious complexity differences by using the CEEMDAN-SE. Then, BPNN and Transformer model were used to forecast the subsequences with low complexity and the subsequences with high complexity, respectively. Finally, the forecasting results of each subsequence were superimposed to obtain the final forecasting result. The simulation was taken from our proposed model and six forecasting models by using the load dataset from a certain area of Spain. The results showed that the MAPE of our proposed CEEMDAN-SE-BPNN-Transformer model was 1.1317%, while the RMSE was 304.40, which was better than the selected six forecasting models. |
| first_indexed | 2024-03-10T03:57:52Z |
| format | Article |
| id | doaj.art-415e4d08c54a460e9ae8aac7d1a9a79e |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T03:57:52Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-415e4d08c54a460e9ae8aac7d1a9a79e2023-11-23T10:51:18ZengMDPI AGEnergies1996-10732022-05-011510365910.3390/en15103659Short-Term Load Forecasting Based on the CEEMDAN-Sample Entropy-BPNN-TransformerShichao Huang0Jing Zhang1Yu He2Xiaofan Fu3Luqin Fan4Gang Yao5Yongjun Wen6College of Electrical Engineering, Guizhou University, Guiyang 550025, ChinaCollege of Electrical Engineering, Guizhou University, Guiyang 550025, ChinaCollege of Electrical Engineering, Guizhou University, Guiyang 550025, ChinaCollege of Electrical Engineering, Guizhou University, Guiyang 550025, ChinaCollege of Electrical Engineering, Guizhou University, Guiyang 550025, ChinaGuizhou Power Grid Company, Guiyang 550001, ChinaPujiang Guangyuan Power Construction Co., Ltd., Pujiang, Jinhua 322200, ChinaAiming at the problem that power load data are stochastic and that it is difficult to obtain accurate forecasting results by a single algorithm, in this paper, a combined forecasting method for short-term power load was proposed based on the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN)-sample entropy (SE), the BP neural network (BPNN), and the Transformer model. Firstly, the power load data were decomposed into several power load subsequences with obvious complexity differences by using the CEEMDAN-SE. Then, BPNN and Transformer model were used to forecast the subsequences with low complexity and the subsequences with high complexity, respectively. Finally, the forecasting results of each subsequence were superimposed to obtain the final forecasting result. The simulation was taken from our proposed model and six forecasting models by using the load dataset from a certain area of Spain. The results showed that the MAPE of our proposed CEEMDAN-SE-BPNN-Transformer model was 1.1317%, while the RMSE was 304.40, which was better than the selected six forecasting models.https://www.mdpi.com/1996-1073/15/10/3659BPNNCEEMDANload forecastingsample entropytransformer |
| spellingShingle | Shichao Huang Jing Zhang Yu He Xiaofan Fu Luqin Fan Gang Yao Yongjun Wen Short-Term Load Forecasting Based on the CEEMDAN-Sample Entropy-BPNN-Transformer Energies BPNN CEEMDAN load forecasting sample entropy transformer |
| title | Short-Term Load Forecasting Based on the CEEMDAN-Sample Entropy-BPNN-Transformer |
| title_full | Short-Term Load Forecasting Based on the CEEMDAN-Sample Entropy-BPNN-Transformer |
| title_fullStr | Short-Term Load Forecasting Based on the CEEMDAN-Sample Entropy-BPNN-Transformer |
| title_full_unstemmed | Short-Term Load Forecasting Based on the CEEMDAN-Sample Entropy-BPNN-Transformer |
| title_short | Short-Term Load Forecasting Based on the CEEMDAN-Sample Entropy-BPNN-Transformer |
| title_sort | short term load forecasting based on the ceemdan sample entropy bpnn transformer |
| topic | BPNN CEEMDAN load forecasting sample entropy transformer |
| url | https://www.mdpi.com/1996-1073/15/10/3659 |
| work_keys_str_mv | AT shichaohuang shorttermloadforecastingbasedontheceemdansampleentropybpnntransformer AT jingzhang shorttermloadforecastingbasedontheceemdansampleentropybpnntransformer AT yuhe shorttermloadforecastingbasedontheceemdansampleentropybpnntransformer AT xiaofanfu shorttermloadforecastingbasedontheceemdansampleentropybpnntransformer AT luqinfan shorttermloadforecastingbasedontheceemdansampleentropybpnntransformer AT gangyao shorttermloadforecastingbasedontheceemdansampleentropybpnntransformer AT yongjunwen shorttermloadforecastingbasedontheceemdansampleentropybpnntransformer |