Short-term microgrid load probability density forecasting method based on k-means-deep learning quantile regression
Traditional short-term load forecasting (STLF) methods for large utility grid systems usually provide the forecasted load with deterministic points. However, deterministic load forecasting cannot reveal the load pattern and uncertainty of controllable load in a microgrid, where the prediction errors...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-08-01
|
| Series: | Energy Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352484722006758 |
| _version_ | 1798033013400928256 |
|---|---|
| author | Zilong Zhao Jinrui Tang Jianchao Liu Ganheng Ge Binyu Xiong Yang Li |
| author_facet | Zilong Zhao Jinrui Tang Jianchao Liu Ganheng Ge Binyu Xiong Yang Li |
| author_sort | Zilong Zhao |
| collection | DOAJ |
| description | Traditional short-term load forecasting (STLF) methods for large utility grid systems usually provide the forecasted load with deterministic points. However, deterministic load forecasting cannot reveal the load pattern and uncertainty of controllable load in a microgrid, where the prediction errors may exceed the expected range due to the high volatility and strong randomness. In order to deal with this matter, a probability density forecasting method is proposed to predict the microgrid load with uncertainty for robust power scheduling in this paper. The proposed probability forecasting method effectively combines several data-driven and statistical algorithms, including the k-means algorithm, quantile regression long short-term memory neural network (QRLSTM), and kernel density estimation (KDE). Firstly, similar days related to the prediction day are selected through the k-means algorithm, and the historical load data of these selected days are divided into two subsets including the training dataset and the testing dataset. Secondly, a QRLSTM-based model is established and used to predict the microgrid load for different quantiles. Finally, the probability density function of the predicted points is obtained by KDE on the target day. The prediction accuracy is evaluated roundly and the results demonstrate that the proposed method can effectively reproduce the probability density distribution of the load and provide noticeably better performance than some benchmark methods. |
| first_indexed | 2024-04-11T20:22:21Z |
| format | Article |
| id | doaj.art-0f1bc659762e4fe7be0e9ccab3b2ce9c |
| institution | Directory Open Access Journal |
| issn | 2352-4847 |
| language | English |
| last_indexed | 2024-04-11T20:22:21Z |
| publishDate | 2022-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy Reports |
| spelling | doaj.art-0f1bc659762e4fe7be0e9ccab3b2ce9c2022-12-22T04:04:46ZengElsevierEnergy Reports2352-48472022-08-01813861397Short-term microgrid load probability density forecasting method based on k-means-deep learning quantile regressionZilong Zhao0Jinrui Tang1Jianchao Liu2Ganheng Ge3Binyu Xiong4Yang Li5School of Automation, Wuhan University of Technology, Wuhan, Hubei 430070, ChinaCorresponding author.; School of Automation, Wuhan University of Technology, Wuhan, Hubei 430070, ChinaSchool of Automation, Wuhan University of Technology, Wuhan, Hubei 430070, ChinaSchool of Automation, Wuhan University of Technology, Wuhan, Hubei 430070, ChinaSchool of Automation, Wuhan University of Technology, Wuhan, Hubei 430070, ChinaSchool of Automation, Wuhan University of Technology, Wuhan, Hubei 430070, ChinaTraditional short-term load forecasting (STLF) methods for large utility grid systems usually provide the forecasted load with deterministic points. However, deterministic load forecasting cannot reveal the load pattern and uncertainty of controllable load in a microgrid, where the prediction errors may exceed the expected range due to the high volatility and strong randomness. In order to deal with this matter, a probability density forecasting method is proposed to predict the microgrid load with uncertainty for robust power scheduling in this paper. The proposed probability forecasting method effectively combines several data-driven and statistical algorithms, including the k-means algorithm, quantile regression long short-term memory neural network (QRLSTM), and kernel density estimation (KDE). Firstly, similar days related to the prediction day are selected through the k-means algorithm, and the historical load data of these selected days are divided into two subsets including the training dataset and the testing dataset. Secondly, a QRLSTM-based model is established and used to predict the microgrid load for different quantiles. Finally, the probability density function of the predicted points is obtained by KDE on the target day. The prediction accuracy is evaluated roundly and the results demonstrate that the proposed method can effectively reproduce the probability density distribution of the load and provide noticeably better performance than some benchmark methods.http://www.sciencedirect.com/science/article/pii/S2352484722006758Short-term load forecastingProbability densityQuantile regressionLong short-term memory neural networkKernel density estimationMicrogrid |
| spellingShingle | Zilong Zhao Jinrui Tang Jianchao Liu Ganheng Ge Binyu Xiong Yang Li Short-term microgrid load probability density forecasting method based on k-means-deep learning quantile regression Energy Reports Short-term load forecasting Probability density Quantile regression Long short-term memory neural network Kernel density estimation Microgrid |
| title | Short-term microgrid load probability density forecasting method based on k-means-deep learning quantile regression |
| title_full | Short-term microgrid load probability density forecasting method based on k-means-deep learning quantile regression |
| title_fullStr | Short-term microgrid load probability density forecasting method based on k-means-deep learning quantile regression |
| title_full_unstemmed | Short-term microgrid load probability density forecasting method based on k-means-deep learning quantile regression |
| title_short | Short-term microgrid load probability density forecasting method based on k-means-deep learning quantile regression |
| title_sort | short term microgrid load probability density forecasting method based on k means deep learning quantile regression |
| topic | Short-term load forecasting Probability density Quantile regression Long short-term memory neural network Kernel density estimation Microgrid |
| url | http://www.sciencedirect.com/science/article/pii/S2352484722006758 |
| work_keys_str_mv | AT zilongzhao shorttermmicrogridloadprobabilitydensityforecastingmethodbasedonkmeansdeeplearningquantileregression AT jinruitang shorttermmicrogridloadprobabilitydensityforecastingmethodbasedonkmeansdeeplearningquantileregression AT jianchaoliu shorttermmicrogridloadprobabilitydensityforecastingmethodbasedonkmeansdeeplearningquantileregression AT ganhengge shorttermmicrogridloadprobabilitydensityforecastingmethodbasedonkmeansdeeplearningquantileregression AT binyuxiong shorttermmicrogridloadprobabilitydensityforecastingmethodbasedonkmeansdeeplearningquantileregression AT yangli shorttermmicrogridloadprobabilitydensityforecastingmethodbasedonkmeansdeeplearningquantileregression |