File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A deep learning model for short-term power load and probability density forecasting

TitleA deep learning model for short-term power load and probability density forecasting
Authors
KeywordsDeep learning
Feature engineering
Power load forecasting
Probability density forecasting
Issue Date2018
Citation
Energy, 2018, v. 160, p. 1186-1200 How to Cite?
AbstractAccurate load forecasting is critical for power system planning and operational decision making. In this study, we are the first to utilize a deep feedforward network for short-term electricity load forecasting. Our results are compared to those of popular machine learning models such as random forest and gradient boosting machine models. Then, electricity consumption patterns are explored based on monthly, weekly and temperature-based patterns in terms of feature importance. Also, a probability density forecasting method based on deep learning, quantile regression and kernel density estimation is proposed. To verify the efficiency of the proposed methods, three case studies based on daily electricity consumption data for three Chinese cities for 2014 are conducted. The empirical results demonstrate that (1) the proposed deep learning-based approach exhibits better forecasting accuracy in terms of measuring electricity consumption relative to the random forest and gradient boosting model; (2) monthly, weekly and weather-related variables are key factors that have a great influence on household electricity consumption; and (3) the proposed probability density forecasting method is capable of forecasting high-quality prediction intervals via probability density forecasting.
Persistent Identifierhttp://hdl.handle.net/10722/333339
ISSN
2021 Impact Factor: 8.857
2020 SCImago Journal Rankings: 1.961
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorGuo, Zhifeng-
dc.contributor.authorZhou, Kaile-
dc.contributor.authorZhang, Xiaoling-
dc.contributor.authorYang, Shanlin-
dc.date.accessioned2023-10-06T05:18:35Z-
dc.date.available2023-10-06T05:18:35Z-
dc.date.issued2018-
dc.identifier.citationEnergy, 2018, v. 160, p. 1186-1200-
dc.identifier.issn0360-5442-
dc.identifier.urihttp://hdl.handle.net/10722/333339-
dc.description.abstractAccurate load forecasting is critical for power system planning and operational decision making. In this study, we are the first to utilize a deep feedforward network for short-term electricity load forecasting. Our results are compared to those of popular machine learning models such as random forest and gradient boosting machine models. Then, electricity consumption patterns are explored based on monthly, weekly and temperature-based patterns in terms of feature importance. Also, a probability density forecasting method based on deep learning, quantile regression and kernel density estimation is proposed. To verify the efficiency of the proposed methods, three case studies based on daily electricity consumption data for three Chinese cities for 2014 are conducted. The empirical results demonstrate that (1) the proposed deep learning-based approach exhibits better forecasting accuracy in terms of measuring electricity consumption relative to the random forest and gradient boosting model; (2) monthly, weekly and weather-related variables are key factors that have a great influence on household electricity consumption; and (3) the proposed probability density forecasting method is capable of forecasting high-quality prediction intervals via probability density forecasting.-
dc.languageeng-
dc.relation.ispartofEnergy-
dc.subjectDeep learning-
dc.subjectFeature engineering-
dc.subjectPower load forecasting-
dc.subjectProbability density forecasting-
dc.titleA deep learning model for short-term power load and probability density forecasting-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.energy.2018.07.090-
dc.identifier.scopuseid_2-s2.0-85053078238-
dc.identifier.volume160-
dc.identifier.spage1186-
dc.identifier.epage1200-
dc.identifier.isiWOS:000445985300098-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats