Mid-Term Energy Demand Forecasting by Hybrid Neuro-Fuzzy Models
This paper proposes a structure for long-term energy demand forecasting. The proposed hybrid approach, called HPLLNF, uses the local linear neuro-fuzzy (LLNF) model as the forecaster and utilizes the Hodrick–Prescott (HP) filter for extraction of the trend and cyclic components of the energy demand...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2011-12-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1996-1073/5/1/1/ |
| _version_ | 1817990625864187904 |
|---|---|
| author | Arash Miranian Majid Abdollahzade Hossein Iranmanesh |
| author_facet | Arash Miranian Majid Abdollahzade Hossein Iranmanesh |
| author_sort | Arash Miranian |
| collection | DOAJ |
| description | This paper proposes a structure for long-term energy demand forecasting. The proposed hybrid approach, called HPLLNF, uses the local linear neuro-fuzzy (LLNF) model as the forecaster and utilizes the Hodrick–Prescott (HP) filter for extraction of the trend and cyclic components of the energy demand series. Besides, the sophisticated technique of mutual information (MI) is employed to select the most relevant input features with least possible redundancies for the forecast model. Each generated component by the HP filter is then modeled through an LLNF model. Starting from an optimal least square estimation, the local linear model tree (LOLIMOT) learning algorithm increases the complexity of the LLNF model as long as its performance is improved. The proposed HPLLNF model with MI-based input selection is applied to the problem of long-term energy forecasting in three different case studies, including forecasting of the gasoline, crude oil and natural gas demand over the next 12 months. The obtained forecasting results reveal the noteworthy performance of the proposed approach for long-term energy demand forecasting applications. |
| first_indexed | 2024-04-14T01:01:40Z |
| format | Article |
| id | doaj.art-bcf3b489db31429a97d5e615fcc3a6c0 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-14T01:01:40Z |
| publishDate | 2011-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-bcf3b489db31429a97d5e615fcc3a6c02022-12-22T02:21:23ZengMDPI AGEnergies1996-10732011-12-015112110.3390/en5010001Mid-Term Energy Demand Forecasting by Hybrid Neuro-Fuzzy ModelsArash MiranianMajid AbdollahzadeHossein IranmaneshThis paper proposes a structure for long-term energy demand forecasting. The proposed hybrid approach, called HPLLNF, uses the local linear neuro-fuzzy (LLNF) model as the forecaster and utilizes the Hodrick–Prescott (HP) filter for extraction of the trend and cyclic components of the energy demand series. Besides, the sophisticated technique of mutual information (MI) is employed to select the most relevant input features with least possible redundancies for the forecast model. Each generated component by the HP filter is then modeled through an LLNF model. Starting from an optimal least square estimation, the local linear model tree (LOLIMOT) learning algorithm increases the complexity of the LLNF model as long as its performance is improved. The proposed HPLLNF model with MI-based input selection is applied to the problem of long-term energy forecasting in three different case studies, including forecasting of the gasoline, crude oil and natural gas demand over the next 12 months. The obtained forecasting results reveal the noteworthy performance of the proposed approach for long-term energy demand forecasting applications.http://www.mdpi.com/1996-1073/5/1/1/local linear neuro-fuzzy (LLNF) modelHodrick–Prescott (HP) filterHPLLNFmutual information (MI)energy demand forecasting |
| spellingShingle | Arash Miranian Majid Abdollahzade Hossein Iranmanesh Mid-Term Energy Demand Forecasting by Hybrid Neuro-Fuzzy Models Energies local linear neuro-fuzzy (LLNF) model Hodrick–Prescott (HP) filter HPLLNF mutual information (MI) energy demand forecasting |
| title | Mid-Term Energy Demand Forecasting by Hybrid Neuro-Fuzzy Models |
| title_full | Mid-Term Energy Demand Forecasting by Hybrid Neuro-Fuzzy Models |
| title_fullStr | Mid-Term Energy Demand Forecasting by Hybrid Neuro-Fuzzy Models |
| title_full_unstemmed | Mid-Term Energy Demand Forecasting by Hybrid Neuro-Fuzzy Models |
| title_short | Mid-Term Energy Demand Forecasting by Hybrid Neuro-Fuzzy Models |
| title_sort | mid term energy demand forecasting by hybrid neuro fuzzy models |
| topic | local linear neuro-fuzzy (LLNF) model Hodrick–Prescott (HP) filter HPLLNF mutual information (MI) energy demand forecasting |
| url | http://www.mdpi.com/1996-1073/5/1/1/ |
| work_keys_str_mv | AT arashmiranian midtermenergydemandforecastingbyhybridneurofuzzymodels AT majidabdollahzade midtermenergydemandforecastingbyhybridneurofuzzymodels AT hosseiniranmanesh midtermenergydemandforecastingbyhybridneurofuzzymodels |