Hybrid Model Based on an SD Selection, CEEMDAN, and Deep Learning for Short-Term Load Forecasting of an Electric Vehicle Fleet
Forecasting the aggregate charging load of a fleet of electric vehicles (EVs) plays an important role in the energy management of the future power system. Therefore, accurate charging load forecasting is necessary for reliable and efficient power system operation. A hybrid method that is a combinati...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/18/9288 |
| _version_ | 1797491379921747968 |
|---|---|
| author | Ahmad Mohsenimanesh Evgueniy Entchev Filip Bosnjak |
| author_facet | Ahmad Mohsenimanesh Evgueniy Entchev Filip Bosnjak |
| author_sort | Ahmad Mohsenimanesh |
| collection | DOAJ |
| description | Forecasting the aggregate charging load of a fleet of electric vehicles (EVs) plays an important role in the energy management of the future power system. Therefore, accurate charging load forecasting is necessary for reliable and efficient power system operation. A hybrid method that is a combination of the similar day (SD) selection, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and deep neural networks is proposed and explored in this paper. For the SD selection, an extreme gradient boosting (XGB)-based weighted k-means method is chosen and applied to evaluate the similarity between the prediction and historical days. The CEEMDAN algorithm, which is an advanced method of empirical mode decomposition (EMD), is used to decompose original data, to acquire intrinsic mode functions (IMFs) and residuals, and to improve the noise reduction effect. Three popular deep neural networks that have been utilized for load predictions are gated recurrent units (GRUs), long short-term memory (LSTM), and bidirectional long short-term memory (BiLSTM). The developed models were assessed on a real-life charging load dataset that was collected from 1000 EVs in nine provinces in Canada from 2017 to 2019. The obtained numerical results of six predictive combination models show that the proposed hybrid SD-CEEMDAN-BiLSTM model outperformed the single and other hybrid models with the smallest forecasting mean absolute percentage error (MAPE) of 2.63% Canada-wide. |
| first_indexed | 2024-03-10T00:47:37Z |
| format | Article |
| id | doaj.art-0031d0c8818148e5ab6d54c614ac4d7d |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T00:47:37Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-0031d0c8818148e5ab6d54c614ac4d7d2023-11-23T14:56:07ZengMDPI AGApplied Sciences2076-34172022-09-011218928810.3390/app12189288Hybrid Model Based on an SD Selection, CEEMDAN, and Deep Learning for Short-Term Load Forecasting of an Electric Vehicle FleetAhmad Mohsenimanesh0Evgueniy Entchev1Filip Bosnjak2Hybrid Energy Systems, CanmetENERGY Ottawa Research Centre, Natural Resources Canada, 1 Haanel Drive, Ottawa, ON K1A 1M1, CanadaHybrid Energy Systems, CanmetENERGY Ottawa Research Centre, Natural Resources Canada, 1 Haanel Drive, Ottawa, ON K1A 1M1, CanadaHybrid Energy Systems, CanmetENERGY Ottawa Research Centre, Natural Resources Canada, 1 Haanel Drive, Ottawa, ON K1A 1M1, CanadaForecasting the aggregate charging load of a fleet of electric vehicles (EVs) plays an important role in the energy management of the future power system. Therefore, accurate charging load forecasting is necessary for reliable and efficient power system operation. A hybrid method that is a combination of the similar day (SD) selection, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and deep neural networks is proposed and explored in this paper. For the SD selection, an extreme gradient boosting (XGB)-based weighted k-means method is chosen and applied to evaluate the similarity between the prediction and historical days. The CEEMDAN algorithm, which is an advanced method of empirical mode decomposition (EMD), is used to decompose original data, to acquire intrinsic mode functions (IMFs) and residuals, and to improve the noise reduction effect. Three popular deep neural networks that have been utilized for load predictions are gated recurrent units (GRUs), long short-term memory (LSTM), and bidirectional long short-term memory (BiLSTM). The developed models were assessed on a real-life charging load dataset that was collected from 1000 EVs in nine provinces in Canada from 2017 to 2019. The obtained numerical results of six predictive combination models show that the proposed hybrid SD-CEEMDAN-BiLSTM model outperformed the single and other hybrid models with the smallest forecasting mean absolute percentage error (MAPE) of 2.63% Canada-wide.https://www.mdpi.com/2076-3417/12/18/9288EVcharging loadSD selectionCEEMDANGRULSTM |
| spellingShingle | Ahmad Mohsenimanesh Evgueniy Entchev Filip Bosnjak Hybrid Model Based on an SD Selection, CEEMDAN, and Deep Learning for Short-Term Load Forecasting of an Electric Vehicle Fleet Applied Sciences EV charging load SD selection CEEMDAN GRU LSTM |
| title | Hybrid Model Based on an SD Selection, CEEMDAN, and Deep Learning for Short-Term Load Forecasting of an Electric Vehicle Fleet |
| title_full | Hybrid Model Based on an SD Selection, CEEMDAN, and Deep Learning for Short-Term Load Forecasting of an Electric Vehicle Fleet |
| title_fullStr | Hybrid Model Based on an SD Selection, CEEMDAN, and Deep Learning for Short-Term Load Forecasting of an Electric Vehicle Fleet |
| title_full_unstemmed | Hybrid Model Based on an SD Selection, CEEMDAN, and Deep Learning for Short-Term Load Forecasting of an Electric Vehicle Fleet |
| title_short | Hybrid Model Based on an SD Selection, CEEMDAN, and Deep Learning for Short-Term Load Forecasting of an Electric Vehicle Fleet |
| title_sort | hybrid model based on an sd selection ceemdan and deep learning for short term load forecasting of an electric vehicle fleet |
| topic | EV charging load SD selection CEEMDAN GRU LSTM |
| url | https://www.mdpi.com/2076-3417/12/18/9288 |
| work_keys_str_mv | AT ahmadmohsenimanesh hybridmodelbasedonansdselectionceemdananddeeplearningforshorttermloadforecastingofanelectricvehiclefleet AT evgueniyentchev hybridmodelbasedonansdselectionceemdananddeeplearningforshorttermloadforecastingofanelectricvehiclefleet AT filipbosnjak hybridmodelbasedonansdselectionceemdananddeeplearningforshorttermloadforecastingofanelectricvehiclefleet |