File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Using Bayesian Deep Learning to Capture Uncertainty for Residential Net Load Forecasting

TitleUsing Bayesian Deep Learning to Capture Uncertainty for Residential Net Load Forecasting
Authors
KeywordsBayesian deep learning
clustering
distributed PV generation
long short-term memory
Probabilistic net load forecasting
Issue Date2020
Citation
IEEE Transactions on Power Systems, 2020, v. 35, n. 1, p. 188-201 How to Cite?
AbstractDecarbonization of electricity systems drives significant and continued investments in distributed energy sources to support the cost-effective transition to low-carbon energy systems. However, the rapid integration of distributed photovoltaic (PV) generation presents great challenges in obtaining reliable and secure grid operations because of its limited visibility and intermittent nature. Under this reality, net load forecasting is facing unprecedented difficulty in answering the following question: How can we accurately predict the net load while capturing the massive uncertainties arising from distributed PV generation and load, especially in the context of high PV penetration? This paper proposes a novel probabilistic day-ahead net load forecasting method to capture both epistemic uncertainty and aleatoric uncertainty using Bayesian deep learning, which is a new field that combines Bayesian probability theory and deep learning. The proposed methodological framework employs clustering in subprofiles and considers residential rooftop PV outputs as input features to enhance the performance of aggregated net load forecasting. Numerical experiments have been carried out based on fine-grained smart meter data from the Australian grid with separately recorded measurements of rooftop PV generation and loads. The results demonstrate the superior performance of the proposed scheme compared with a series of state-of-the-art methods and indicate the importance and effectiveness of subprofile clustering and high PV visibility.
Persistent Identifierhttp://hdl.handle.net/10722/308805
ISSN
2023 Impact Factor: 6.5
2023 SCImago Journal Rankings: 3.827
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorSun, Mingyang-
dc.contributor.authorZhang, Tingqi-
dc.contributor.authorWang, Yi-
dc.contributor.authorStrbac, Goran-
dc.contributor.authorKang, Chongqing-
dc.date.accessioned2021-12-08T07:50:10Z-
dc.date.available2021-12-08T07:50:10Z-
dc.date.issued2020-
dc.identifier.citationIEEE Transactions on Power Systems, 2020, v. 35, n. 1, p. 188-201-
dc.identifier.issn0885-8950-
dc.identifier.urihttp://hdl.handle.net/10722/308805-
dc.description.abstractDecarbonization of electricity systems drives significant and continued investments in distributed energy sources to support the cost-effective transition to low-carbon energy systems. However, the rapid integration of distributed photovoltaic (PV) generation presents great challenges in obtaining reliable and secure grid operations because of its limited visibility and intermittent nature. Under this reality, net load forecasting is facing unprecedented difficulty in answering the following question: How can we accurately predict the net load while capturing the massive uncertainties arising from distributed PV generation and load, especially in the context of high PV penetration? This paper proposes a novel probabilistic day-ahead net load forecasting method to capture both epistemic uncertainty and aleatoric uncertainty using Bayesian deep learning, which is a new field that combines Bayesian probability theory and deep learning. The proposed methodological framework employs clustering in subprofiles and considers residential rooftop PV outputs as input features to enhance the performance of aggregated net load forecasting. Numerical experiments have been carried out based on fine-grained smart meter data from the Australian grid with separately recorded measurements of rooftop PV generation and loads. The results demonstrate the superior performance of the proposed scheme compared with a series of state-of-the-art methods and indicate the importance and effectiveness of subprofile clustering and high PV visibility.-
dc.languageeng-
dc.relation.ispartofIEEE Transactions on Power Systems-
dc.subjectBayesian deep learning-
dc.subjectclustering-
dc.subjectdistributed PV generation-
dc.subjectlong short-term memory-
dc.subjectProbabilistic net load forecasting-
dc.titleUsing Bayesian Deep Learning to Capture Uncertainty for Residential Net Load Forecasting-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TPWRS.2019.2924294-
dc.identifier.scopuseid_2-s2.0-85078405282-
dc.identifier.volume35-
dc.identifier.issue1-
dc.identifier.spage188-
dc.identifier.epage201-
dc.identifier.eissn1558-0679-
dc.identifier.isiWOS:000509344600017-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats