Repository logo
 
Publication

Regression modeling for enterprise electricity consumption: A comparison of recurrent neural network and its variants

2021-03Journal article Restricted access
Simple item page
dc.contributor.authorBai, Yun
dc.contributor.authorXie, Jingjing
dc.contributor.authorLiu, Chao
dc.contributor.authorTao, Ying
dc.contributor.authorZeng, Bo
dc.contributor.authorLi, Chuan
dc.date.accessioned2021-09-08T10:58:04Z
dc.date.available2021-09-08T10:58:04Z
dc.date.issued2021-03
dc.description.abstractEffective electricity consumption forecasting is extremely significant for enterprises' electricity planning which can provide data support for production decision, thus improving the level of enterprises' clean production. In recent years, recurrent neural network (RNN) and its variants have led to extensive research for time series forecasting. However, the performance and selection of these models in enterprise electricity forecasting have not been reported. With this study, we attempted to back some of these solutions with experimental results. This paper focused on a comparison for daily enterprise electricity consumption forecasting using different RNN models, i.e, standard RNN, long short-term memory-based RNN (LSTM), and gated recurrent unit-based RNN (GRU). To test their regression performance, three Chinese enterprises with different scales of electricity consumption are investigated. The comparison results show that the LSTM and the GRU models are slightly better than that of the RNN in terms of normalized root-mean-square error, mean absolute percentage error and threshold statistic. Moreover, the GRU model with the simplest structure is significantly different from the RNN, but not from LSTM in terms of Friedman testing. Hence the GRU model can be regarded as the first candidate for the enterprise electricity consumption forecasting in the future work.
dc.description.sponsorshipNational Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [71801044]; Humanities and Social Science Foundation of Ministry of Education of ChinaMinistry of Education, China [17YJC630003]; Natural Science Foundation of ChongqingNatural Science Foundation of Chongqing [cstc2018jcyjAX0436]; Project of China Scholarship Council [201908500020]; Open Grant of Chongqing Technology and Business University [KFJJ2018106, 1756012]
dc.description.versioninfo:eu-repo/semantics/publishedVersion
dc.identifier.doi10.1016/j.ijepes.2020.106612
dc.identifier.issn0142-0615
dc.identifier.urihttp://hdl.handle.net/10400.1/17022
dc.language.isoeng
dc.peerreviewedyes
dc.publisherELSEVIER SCI LTD
dc.subjectEnterprise electricity consumption
dc.subjectRecurrent neural network
dc.subjectLong short-term memory
dc.subjectGated recurrent unit
dc.subjectForecast
dc.subject.otherEngineering
dc.titleRegression modeling for enterprise electricity consumption: A comparison of recurrent neural network and its variants
dc.typejournal article
dspace.entity.typePublication
oaire.citation.startPage106612
oaire.citation.titleInternational Journal of Electrical Power & Energy Systems
oaire.citation.volume126
person.familyNameBai
person.givenNameYun
person.identifier.orcid0000-0003-2710-7994
person.identifier.scopus-author-id55461096500
rcaap.rightsrestrictedAccess
rcaap.typearticle
relation.isAuthorOfPublication395ae945-8e87-47b3-9edf-6fa1f380097f
relation.isAuthorOfPublication.latestForDiscovery395ae945-8e87-47b3-9edf-6fa1f380097f

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
1-s2.0-S0142061520319967-main.pdf
Size:
1.08 MB
Format:
Adobe Portable Document Format
Download

Collections

FCT2-Artigos (em revistas ou actas indexadas)