Sökning: onr:"swepub:oai:DiVA.org:kth-322798" >
Scenario Generation...
Scenario Generations for Renewable Energy Sources and Loads Based on Implicit Maximum Likelihood Estimations
-
- Liao, Wenlong (författare)
- Aalborg Univ, AAU Energy, Aalborg, Denmark.
-
- Bak-Jensen, Birgitte (författare)
- Aalborg Univ, AAU Energy, Aalborg, Denmark.
-
- Pillai, Jayakrishnan Radhakrishna (författare)
- Aalborg Univ, AAU Energy, Aalborg, Denmark.
-
visa fler...
-
- Yang, Zhe (författare)
- Aalborg Univ, AAU Energy, Aalborg, Denmark.
-
- Wang, Yusen (författare)
- KTH,Teknisk informationsvetenskap
-
- Liu, Kuangpu (författare)
- Aalborg Univ, AAU Energy, Aalborg, Denmark.
-
visa färre...
-
Aalborg Univ, AAU Energy, Aalborg, Denmark Teknisk informationsvetenskap (creator_code:org_t)
- Journal of Modern Power Systems and Clean Energy, 2022
- 2022
- Engelska.
-
Ingår i: Journal of Modern Power Systems and Clean Energy. - : Journal of Modern Power Systems and Clean Energy. - 2196-5625 .- 2196-5420. ; 10:6, s. 1563-1575
- Relaterad länk:
-
https://doi.org/10.3...
-
visa fler...
-
https://urn.kb.se/re...
-
https://doi.org/10.3...
-
visa färre...
Abstract
Ämnesord
Stäng
- 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.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Naturresursteknik -- Energisystem (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Environmental Engineering -- Energy Systems (hsv//eng)
Nyckelord
- Renewable energy source
- scenario generation
- implicit maximum likelihood estimation (IMLE)
- deep learning
- generative network
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas