A direct prediction method for wind power ramp events considering the class imbalanced problem
Abstract Predicting wind power ramp events directly based on the historical ramp event time series has drawn increasing attention recently. But the class imbalance problem of the ramp event time series significantly affects the prediction accuracy of ramp events. In the present study, a layer oversa...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-05-01
|
| Series: | Energy Science & Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/ese3.1415 |
| _version_ | 1827950490601652224 |
|---|---|
| author | Guorui Ren Jie Wan Yanjia Wang Kun Yao Junfeng Fu Jilai Yu |
| author_facet | Guorui Ren Jie Wan Yanjia Wang Kun Yao Junfeng Fu Jilai Yu |
| author_sort | Guorui Ren |
| collection | DOAJ |
| description | Abstract Predicting wind power ramp events directly based on the historical ramp event time series has drawn increasing attention recently. But the class imbalance problem of the ramp event time series significantly affects the prediction accuracy of ramp events. In the present study, a layer oversampling (LOS) method is proposed considering the relation characteristics of wind power amplitudes and the occurrence frequency of wind power ramp events. Meanwhile, a hybrid sampling method of error bootstrap‐LOS (EB‐LOS) is proposed by combining LOS with the EB oversampling method. After balancing the samples of the ramp and nonramp events by using different sampling methods, the backpropagation neural network (BPNN), and the long short‐term memory (LSTM) methods are employed to directly predict ramp events based on historical data collected from eight wind farms. Comparison results proved that the proposed EB‐LOS method achieves the best prediction performance with an average recall of 0.8196 when using the BPNN model to directly predict ramp events. The best prediction performance of the EB‐LOS method is also proved by using the LSTM model to directly predict ramp events. |
| first_indexed | 2024-04-09T13:26:09Z |
| format | Article |
| id | doaj.art-3951d1108083491393ea2683024c5079 |
| institution | Directory Open Access Journal |
| issn | 2050-0505 |
| language | English |
| last_indexed | 2024-04-09T13:26:09Z |
| publishDate | 2023-05-01 |
| publisher | Wiley |
| record_format | Article |
| series | Energy Science & Engineering |
| spelling | doaj.art-3951d1108083491393ea2683024c50792023-05-10T07:56:55ZengWileyEnergy Science & Engineering2050-05052023-05-011151705171510.1002/ese3.1415A direct prediction method for wind power ramp events considering the class imbalanced problemGuorui Ren0Jie Wan1Yanjia Wang2Kun Yao3Junfeng Fu4Jilai Yu5School of Control and Computer Engineering North China Electric Power University Beijing ChinaSchool of Electrical Engineering and Automation Harbin Institute of Technology Harbin ChinaSchool of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai ChinaSchool of Electrical Engineering and Automation Harbin Institute of Technology Harbin ChinaSchool of Electrical Engineering and Automation Harbin Institute of Technology Harbin ChinaSchool of Electrical Engineering and Automation Harbin Institute of Technology Harbin ChinaAbstract Predicting wind power ramp events directly based on the historical ramp event time series has drawn increasing attention recently. But the class imbalance problem of the ramp event time series significantly affects the prediction accuracy of ramp events. In the present study, a layer oversampling (LOS) method is proposed considering the relation characteristics of wind power amplitudes and the occurrence frequency of wind power ramp events. Meanwhile, a hybrid sampling method of error bootstrap‐LOS (EB‐LOS) is proposed by combining LOS with the EB oversampling method. After balancing the samples of the ramp and nonramp events by using different sampling methods, the backpropagation neural network (BPNN), and the long short‐term memory (LSTM) methods are employed to directly predict ramp events based on historical data collected from eight wind farms. Comparison results proved that the proposed EB‐LOS method achieves the best prediction performance with an average recall of 0.8196 when using the BPNN model to directly predict ramp events. The best prediction performance of the EB‐LOS method is also proved by using the LSTM model to directly predict ramp events.https://doi.org/10.1002/ese3.1415class imbalancedirect predictionlayer oversamplingramp eventrelation characteristicswind power amplitudes |
| spellingShingle | Guorui Ren Jie Wan Yanjia Wang Kun Yao Junfeng Fu Jilai Yu A direct prediction method for wind power ramp events considering the class imbalanced problem Energy Science & Engineering class imbalance direct prediction layer oversampling ramp event relation characteristics wind power amplitudes |
| title | A direct prediction method for wind power ramp events considering the class imbalanced problem |
| title_full | A direct prediction method for wind power ramp events considering the class imbalanced problem |
| title_fullStr | A direct prediction method for wind power ramp events considering the class imbalanced problem |
| title_full_unstemmed | A direct prediction method for wind power ramp events considering the class imbalanced problem |
| title_short | A direct prediction method for wind power ramp events considering the class imbalanced problem |
| title_sort | direct prediction method for wind power ramp events considering the class imbalanced problem |
| topic | class imbalance direct prediction layer oversampling ramp event relation characteristics wind power amplitudes |
| url | https://doi.org/10.1002/ese3.1415 |
| work_keys_str_mv | AT guoruiren adirectpredictionmethodforwindpowerrampeventsconsideringtheclassimbalancedproblem AT jiewan adirectpredictionmethodforwindpowerrampeventsconsideringtheclassimbalancedproblem AT yanjiawang adirectpredictionmethodforwindpowerrampeventsconsideringtheclassimbalancedproblem AT kunyao adirectpredictionmethodforwindpowerrampeventsconsideringtheclassimbalancedproblem AT junfengfu adirectpredictionmethodforwindpowerrampeventsconsideringtheclassimbalancedproblem AT jilaiyu adirectpredictionmethodforwindpowerrampeventsconsideringtheclassimbalancedproblem AT guoruiren directpredictionmethodforwindpowerrampeventsconsideringtheclassimbalancedproblem AT jiewan directpredictionmethodforwindpowerrampeventsconsideringtheclassimbalancedproblem AT yanjiawang directpredictionmethodforwindpowerrampeventsconsideringtheclassimbalancedproblem AT kunyao directpredictionmethodforwindpowerrampeventsconsideringtheclassimbalancedproblem AT junfengfu directpredictionmethodforwindpowerrampeventsconsideringtheclassimbalancedproblem AT jilaiyu directpredictionmethodforwindpowerrampeventsconsideringtheclassimbalancedproblem |