Scenario Generations for Renewable Energy Sources and Loads Based on Implicit Maximum Likelihood Estimations
Scenario generations for renewable energy sources and loads play an important role in the stable operation and risk assessment of integrated energy systems. This paper proposes a deep generative network based method to model time-series curves, e.g., power generation curves and load curves, of renew...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | Journal of Modern Power Systems and Clean Energy |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9841522/ |
| _version_ | 1811319083226890240 |
|---|---|
| author | Wenlong Liao Birgitte Bak-Jensen Jayakrishnan Radhakrishna Pillai Zhe Yang Yusen Wang Kuangpu Liu |
| author_facet | Wenlong Liao Birgitte Bak-Jensen Jayakrishnan Radhakrishna Pillai Zhe Yang Yusen Wang Kuangpu Liu |
| author_sort | Wenlong Liao |
| collection | DOAJ |
| description | Scenario generations for renewable energy sources and loads play an important role in the stable operation and risk assessment of integrated energy systems. This paper proposes a deep generative network based method to model time-series curves, e.g., power generation curves and load curves, of renewable energy sources and loads based on implicit maximum likelihood estimations (IMLEs), which can generate realistic scenarios with similar patterns as real ones. After training the model, any number of new scenarios can be obtained by simply inputting Gaussian noises into the data generator of IMLEs. The proposed approach does not require any model assumptions or prior knowledge of the form in the likelihood function being made during the training process, which leads to stronger applicability than explicit density model based methods. The extensive experiments show that the IMLEs accurately capture the complex shapes, frequency-domain characteristics, probability distributions, and correlations of renewable energy sources and loads. Moreover, the proposed approach can be easily generalized to scenario generation tasks of various renewable energy sources and loads by fine-tuning parameters and structures. |
| first_indexed | 2024-04-13T12:36:59Z |
| format | Article |
| id | doaj.art-2b5c7cf03d374a0cbf673b697b62fcae |
| institution | Directory Open Access Journal |
| issn | 2196-5420 |
| language | English |
| last_indexed | 2024-04-13T12:36:59Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | Journal of Modern Power Systems and Clean Energy |
| spelling | doaj.art-2b5c7cf03d374a0cbf673b697b62fcae2022-12-22T02:46:37ZengIEEEJournal of Modern Power Systems and Clean Energy2196-54202022-01-011061563157510.35833/MPCE.2022.0001089841522Scenario Generations for Renewable Energy Sources and Loads Based on Implicit Maximum Likelihood EstimationsWenlong Liao0Birgitte Bak-Jensen1Jayakrishnan Radhakrishna Pillai2Zhe Yang3Yusen Wang4Kuangpu Liu5AAU Energy, Aalborg University,Aalborg,DenmarkAAU Energy, Aalborg University,Aalborg,DenmarkAAU Energy, Aalborg University,Aalborg,DenmarkAAU Energy, Aalborg University,Aalborg,DenmarkSchool of Electrical Engineering and Computer Science, KTH Royal Institute of Technology,Stockholm,SwedenAAU Energy, Aalborg University,Aalborg,DenmarkScenario generations for renewable energy sources and loads play an important role in the stable operation and risk assessment of integrated energy systems. This paper proposes a deep generative network based method to model time-series curves, e.g., power generation curves and load curves, of renewable energy sources and loads based on implicit maximum likelihood estimations (IMLEs), which can generate realistic scenarios with similar patterns as real ones. After training the model, any number of new scenarios can be obtained by simply inputting Gaussian noises into the data generator of IMLEs. The proposed approach does not require any model assumptions or prior knowledge of the form in the likelihood function being made during the training process, which leads to stronger applicability than explicit density model based methods. The extensive experiments show that the IMLEs accurately capture the complex shapes, frequency-domain characteristics, probability distributions, and correlations of renewable energy sources and loads. Moreover, the proposed approach can be easily generalized to scenario generation tasks of various renewable energy sources and loads by fine-tuning parameters and structures.https://ieeexplore.ieee.org/document/9841522/Renewable energy sourcescenario generationimplicit maximum likelihood estimation (IMLE)deep learninggenerative network |
| spellingShingle | Wenlong Liao Birgitte Bak-Jensen Jayakrishnan Radhakrishna Pillai Zhe Yang Yusen Wang Kuangpu Liu Scenario Generations for Renewable Energy Sources and Loads Based on Implicit Maximum Likelihood Estimations Journal of Modern Power Systems and Clean Energy Renewable energy source scenario generation implicit maximum likelihood estimation (IMLE) deep learning generative network |
| title | Scenario Generations for Renewable Energy Sources and Loads Based on Implicit Maximum Likelihood Estimations |
| title_full | Scenario Generations for Renewable Energy Sources and Loads Based on Implicit Maximum Likelihood Estimations |
| title_fullStr | Scenario Generations for Renewable Energy Sources and Loads Based on Implicit Maximum Likelihood Estimations |
| title_full_unstemmed | Scenario Generations for Renewable Energy Sources and Loads Based on Implicit Maximum Likelihood Estimations |
| title_short | Scenario Generations for Renewable Energy Sources and Loads Based on Implicit Maximum Likelihood Estimations |
| title_sort | scenario generations for renewable energy sources and loads based on implicit maximum likelihood estimations |
| topic | Renewable energy source scenario generation implicit maximum likelihood estimation (IMLE) deep learning generative network |
| url | https://ieeexplore.ieee.org/document/9841522/ |
| work_keys_str_mv | AT wenlongliao scenariogenerationsforrenewableenergysourcesandloadsbasedonimplicitmaximumlikelihoodestimations AT birgittebakjensen scenariogenerationsforrenewableenergysourcesandloadsbasedonimplicitmaximumlikelihoodestimations AT jayakrishnanradhakrishnapillai scenariogenerationsforrenewableenergysourcesandloadsbasedonimplicitmaximumlikelihoodestimations AT zheyang scenariogenerationsforrenewableenergysourcesandloadsbasedonimplicitmaximumlikelihoodestimations AT yusenwang scenariogenerationsforrenewableenergysourcesandloadsbasedonimplicitmaximumlikelihoodestimations AT kuangpuliu scenariogenerationsforrenewableenergysourcesandloadsbasedonimplicitmaximumlikelihoodestimations |