Short-Term Probability Density Function Forecasting of Industrial Loads Based on ConvLSTM-MDN
Load forecasting for industrial customers is essential for reliable operation decisions in the electric power industry. However, most of the load forecasting literature has been focused on deterministic load forecasting (DLF) without considering information on the uncertainty of industrial load. Thi...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-04-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2022.891680/full |
| _version_ | 1818479206018842624 |
|---|---|
| author | Yuan Y. Wang Ting Y. Wang Xiao Q. Chen Xiang J. Zeng Jing J. Huang Xia F. Tang |
| author_facet | Yuan Y. Wang Ting Y. Wang Xiao Q. Chen Xiang J. Zeng Jing J. Huang Xia F. Tang |
| author_sort | Yuan Y. Wang |
| collection | DOAJ |
| description | Load forecasting for industrial customers is essential for reliable operation decisions in the electric power industry. However, most of the load forecasting literature has been focused on deterministic load forecasting (DLF) without considering information on the uncertainty of industrial load. This article proposes a probabilistic density load forecasting model comprising convolutional long short-term memory (ConvLSTM) and a mixture density network (MDN). First, a sliding window strategy is adopted to convert one-dimensional (1D) data into two-dimensional (2D) matrices to reconstruct input features. Then the ConvLSTM is utilized to capture the deep information of the input features. At last, the mixture density network capable of directly predicting probability density functions of loads is adopted. Experimental results on the load datasets of three different industries show the accuracy and reliability of the proposed method. |
| first_indexed | 2024-12-10T09:57:43Z |
| format | Article |
| id | doaj.art-63fe2c0fb2194ea3a16bd045c4cf9bb7 |
| institution | Directory Open Access Journal |
| issn | 2296-598X |
| language | English |
| last_indexed | 2024-12-10T09:57:43Z |
| publishDate | 2022-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj.art-63fe2c0fb2194ea3a16bd045c4cf9bb72022-12-22T01:53:25ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2022-04-011010.3389/fenrg.2022.891680891680Short-Term Probability Density Function Forecasting of Industrial Loads Based on ConvLSTM-MDNYuan Y. Wang0Ting Y. Wang1Xiao Q. Chen2Xiang J. Zeng3Jing J. Huang4Xia F. Tang5Changsha University of Science and Technology, Changsha, ChinaChangsha University of Science and Technology, Changsha, ChinaCalifornia Institute of Technology, Pasadena, CA, United StatesChangsha University of Science and Technology, Changsha, ChinaChangsha University of Science and Technology, Changsha, ChinaChangsha University of Science and Technology, Changsha, ChinaLoad forecasting for industrial customers is essential for reliable operation decisions in the electric power industry. However, most of the load forecasting literature has been focused on deterministic load forecasting (DLF) without considering information on the uncertainty of industrial load. This article proposes a probabilistic density load forecasting model comprising convolutional long short-term memory (ConvLSTM) and a mixture density network (MDN). First, a sliding window strategy is adopted to convert one-dimensional (1D) data into two-dimensional (2D) matrices to reconstruct input features. Then the ConvLSTM is utilized to capture the deep information of the input features. At last, the mixture density network capable of directly predicting probability density functions of loads is adopted. Experimental results on the load datasets of three different industries show the accuracy and reliability of the proposed method.https://www.frontiersin.org/articles/10.3389/fenrg.2022.891680/fullload forecastingprobability densityconvolutional long short-term memorymixture density networkindustrial customers |
| spellingShingle | Yuan Y. Wang Ting Y. Wang Xiao Q. Chen Xiang J. Zeng Jing J. Huang Xia F. Tang Short-Term Probability Density Function Forecasting of Industrial Loads Based on ConvLSTM-MDN Frontiers in Energy Research load forecasting probability density convolutional long short-term memory mixture density network industrial customers |
| title | Short-Term Probability Density Function Forecasting of Industrial Loads Based on ConvLSTM-MDN |
| title_full | Short-Term Probability Density Function Forecasting of Industrial Loads Based on ConvLSTM-MDN |
| title_fullStr | Short-Term Probability Density Function Forecasting of Industrial Loads Based on ConvLSTM-MDN |
| title_full_unstemmed | Short-Term Probability Density Function Forecasting of Industrial Loads Based on ConvLSTM-MDN |
| title_short | Short-Term Probability Density Function Forecasting of Industrial Loads Based on ConvLSTM-MDN |
| title_sort | short term probability density function forecasting of industrial loads based on convlstm mdn |
| topic | load forecasting probability density convolutional long short-term memory mixture density network industrial customers |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2022.891680/full |
| work_keys_str_mv | AT yuanywang shorttermprobabilitydensityfunctionforecastingofindustrialloadsbasedonconvlstmmdn AT tingywang shorttermprobabilitydensityfunctionforecastingofindustrialloadsbasedonconvlstmmdn AT xiaoqchen shorttermprobabilitydensityfunctionforecastingofindustrialloadsbasedonconvlstmmdn AT xiangjzeng shorttermprobabilitydensityfunctionforecastingofindustrialloadsbasedonconvlstmmdn AT jingjhuang shorttermprobabilitydensityfunctionforecastingofindustrialloadsbasedonconvlstmmdn AT xiaftang shorttermprobabilitydensityfunctionforecastingofindustrialloadsbasedonconvlstmmdn |