A hybrid model for China's power grid investment demand forecasting based on variational mode decomposition, regularized extreme learning machine and support vector machine
With the continuous maturity of China's power grid as well as the advancement of electricity market reform in China, accurate and efficient investment decision has become an inevitable requirement of power grid enterprises. However, China's Power grid investment demand has complicated nonl...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2019-01-01
|
| Series: | E3S Web of Conferences |
| Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2019/48/e3sconf_reee2019_03002.pdf |
| _version_ | 1818959687682359296 |
|---|---|
| author | Wu Qianqian Zhu Shaowen Li Jinchao Chen Wenjun Wu Yunna |
| author_facet | Wu Qianqian Zhu Shaowen Li Jinchao Chen Wenjun Wu Yunna |
| author_sort | Wu Qianqian |
| collection | DOAJ |
| description | With the continuous maturity of China's power grid as well as the advancement of electricity market reform in China, accurate and efficient investment decision has become an inevitable requirement of power grid enterprises. However, China's Power grid investment demand has complicated nonlinear and non-stationary characteristics due to it's complex causes of formation, thus make it hard to be forecasted. Aiming at this problem, this paper puts forward a novel hybrid VMD-RELMLOO-PSOSVM forecasting model based on variational mode decomposition (VMD), leave-one-out cross validation error based optimal regularized extreme learning machine (RELM-LOO) and support vector machines optimized by particle swarm optimization algorithm (PSO-SVM). Firstly, the VMD method is employed to decompose the original power grid investment data sequence into several modes which have specific sparsity properties while producing main signal. Then, according to the different characteristics of each subsequence, the RELM-LOO and PSO-SVM model will be used to forecast different modes, respectively; Next, the prediction results of all modes are aggregated to obtain the final prediction results of China's power grid investment demand. Finally, this paper predicts China's power grid investment demand from 2018 to 2020 under 5 different scenarios based on the proposed VMD-RELMLOO-PSOSVM hybrid forecasting model. |
| first_indexed | 2024-12-20T11:45:36Z |
| format | Article |
| id | doaj.art-16bb58c84caa4afcbe5045b63b385b03 |
| institution | Directory Open Access Journal |
| issn | 2267-1242 |
| language | English |
| last_indexed | 2024-12-20T11:45:36Z |
| publishDate | 2019-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | E3S Web of Conferences |
| spelling | doaj.art-16bb58c84caa4afcbe5045b63b385b032022-12-21T19:41:52ZengEDP SciencesE3S Web of Conferences2267-12422019-01-011220300210.1051/e3sconf/201912203002e3sconf_reee2019_03002A hybrid model for China's power grid investment demand forecasting based on variational mode decomposition, regularized extreme learning machine and support vector machineWu QianqianZhu ShaowenLi JinchaoChen WenjunWu YunnaWith the continuous maturity of China's power grid as well as the advancement of electricity market reform in China, accurate and efficient investment decision has become an inevitable requirement of power grid enterprises. However, China's Power grid investment demand has complicated nonlinear and non-stationary characteristics due to it's complex causes of formation, thus make it hard to be forecasted. Aiming at this problem, this paper puts forward a novel hybrid VMD-RELMLOO-PSOSVM forecasting model based on variational mode decomposition (VMD), leave-one-out cross validation error based optimal regularized extreme learning machine (RELM-LOO) and support vector machines optimized by particle swarm optimization algorithm (PSO-SVM). Firstly, the VMD method is employed to decompose the original power grid investment data sequence into several modes which have specific sparsity properties while producing main signal. Then, according to the different characteristics of each subsequence, the RELM-LOO and PSO-SVM model will be used to forecast different modes, respectively; Next, the prediction results of all modes are aggregated to obtain the final prediction results of China's power grid investment demand. Finally, this paper predicts China's power grid investment demand from 2018 to 2020 under 5 different scenarios based on the proposed VMD-RELMLOO-PSOSVM hybrid forecasting model.https://www.e3s-conferences.org/articles/e3sconf/pdf/2019/48/e3sconf_reee2019_03002.pdf |
| spellingShingle | Wu Qianqian Zhu Shaowen Li Jinchao Chen Wenjun Wu Yunna A hybrid model for China's power grid investment demand forecasting based on variational mode decomposition, regularized extreme learning machine and support vector machine E3S Web of Conferences |
| title | A hybrid model for China's power grid investment demand forecasting based on variational mode decomposition, regularized extreme learning machine and support vector
machine |
| title_full | A hybrid model for China's power grid investment demand forecasting based on variational mode decomposition, regularized extreme learning machine and support vector
machine |
| title_fullStr | A hybrid model for China's power grid investment demand forecasting based on variational mode decomposition, regularized extreme learning machine and support vector
machine |
| title_full_unstemmed | A hybrid model for China's power grid investment demand forecasting based on variational mode decomposition, regularized extreme learning machine and support vector
machine |
| title_short | A hybrid model for China's power grid investment demand forecasting based on variational mode decomposition, regularized extreme learning machine and support vector
machine |
| title_sort | hybrid model for china s power grid investment demand forecasting based on variational mode decomposition regularized extreme learning machine and support vector machine |
| url | https://www.e3s-conferences.org/articles/e3sconf/pdf/2019/48/e3sconf_reee2019_03002.pdf |
| work_keys_str_mv | AT wuqianqian ahybridmodelforchinaspowergridinvestmentdemandforecastingbasedonvariationalmodedecompositionregularizedextremelearningmachineandsupportvectormachine AT zhushaowen ahybridmodelforchinaspowergridinvestmentdemandforecastingbasedonvariationalmodedecompositionregularizedextremelearningmachineandsupportvectormachine AT lijinchao ahybridmodelforchinaspowergridinvestmentdemandforecastingbasedonvariationalmodedecompositionregularizedextremelearningmachineandsupportvectormachine AT chenwenjun ahybridmodelforchinaspowergridinvestmentdemandforecastingbasedonvariationalmodedecompositionregularizedextremelearningmachineandsupportvectormachine AT wuyunna ahybridmodelforchinaspowergridinvestmentdemandforecastingbasedonvariationalmodedecompositionregularizedextremelearningmachineandsupportvectormachine AT wuqianqian hybridmodelforchinaspowergridinvestmentdemandforecastingbasedonvariationalmodedecompositionregularizedextremelearningmachineandsupportvectormachine AT zhushaowen hybridmodelforchinaspowergridinvestmentdemandforecastingbasedonvariationalmodedecompositionregularizedextremelearningmachineandsupportvectormachine AT lijinchao hybridmodelforchinaspowergridinvestmentdemandforecastingbasedonvariationalmodedecompositionregularizedextremelearningmachineandsupportvectormachine AT chenwenjun hybridmodelforchinaspowergridinvestmentdemandforecastingbasedonvariationalmodedecompositionregularizedextremelearningmachineandsupportvectormachine AT wuyunna hybridmodelforchinaspowergridinvestmentdemandforecastingbasedonvariationalmodedecompositionregularizedextremelearningmachineandsupportvectormachine |