Publication
A Contextual Reinforcement Learning Approach for Electricity Consumption Forecasting in Buildings
| dc.contributor.author | Ramos, Daniel | |
| dc.contributor.author | Faria, Pedro | |
| dc.contributor.author | Gomes, Luis | |
| dc.contributor.author | Vale, Zita | |
| dc.date.accessioned | 2023-02-01T16:17:26Z | |
| dc.date.available | 2023-02-01T16:17:26Z | |
| dc.date.issued | 2022 | |
| dc.description.abstract | The energy management of buildings plays a vital role in the energy sector. With that in mind, and targeting an accurate forecast of electricity consumption, in the present paper is aimed to provide decision on the best prediction algorithm for each context. It may also increase energy usage related with renewables. In this way, the identification of different contexts is an advantage that may improve prediction accuracy. This paper proposes an innovative approach where a decision tree is used to identify different contexts in energy patterns. One week of five-minutes data sampling is used to test the proposed methodology. Each context is evaluated with a decision criterion based on reinforcement learning to find the best suitable forecasting algorithm. Two forecasting models are approached in this paper, based on K-Nearest Neighbor and Artificial Neural Networks, to illustrate the application of the proposed methodology. The reinforcement learning criterion consists of using the Multiarmed Bandit algorithm. The obtained results validate the adequacy of the proposed methodology in two case-studies: building; and industry. | pt_PT |
| dc.description.sponsorship | This article is a result of the project REal-Time support Infrastructure and Energy management for Intelligent carbon-Neutral smArt cities (RETINA) (NORTE-01-0145-FEDER-000062), supported by Norte Portugal Regional Operational Programme (NORTE 2020), under the PORTUGAL 2020 Partnership Agreement, through the European Regional Development Fund (ERDF), and grant CEECIND/02887/2017. The authors acknowledge the work facilities and equipment provided by the Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development (GECAD) research center (UIDB/00760/2020) to the project team. | pt_PT |
| dc.description.version | info:eu-repo/semantics/publishedVersion | pt_PT |
| dc.identifier.doi | 10.1109/ACCESS.2022.3180754 | pt_PT |
| dc.identifier.uri | http://hdl.handle.net/10400.22/22081 | |
| dc.language.iso | eng | pt_PT |
| dc.peerreviewed | yes | pt_PT |
| dc.publisher | IEEE | pt_PT |
| dc.relation | NORTE-01-0145-FEDER-000062 | pt_PT |
| dc.relation | Not Available | |
| dc.relation | Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development | |
| dc.relation.publisherversion | https://ieeexplore.ieee.org/document/9791389 | pt_PT |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | pt_PT |
| dc.subject | Consumption forecast | pt_PT |
| dc.subject | Contextual operation | pt_PT |
| dc.subject | Decision tree | pt_PT |
| dc.subject | Reinforcement learning | pt_PT |
| dc.title | A Contextual Reinforcement Learning Approach for Electricity Consumption Forecasting in Buildings | pt_PT |
| dc.type | journal article | |
| dspace.entity.type | Publication | |
| oaire.awardTitle | Not Available | |
| oaire.awardTitle | Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development | |
| oaire.awardURI | info:eu-repo/grantAgreement/FCT/CEEC IND 2017/CEECIND%2F02887%2F2017%2FCP1417%2FCT0003/PT | |
| oaire.awardURI | info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F00760%2F2020/PT | |
| oaire.citation.endPage | 61374 | pt_PT |
| oaire.citation.startPage | 61366 | pt_PT |
| oaire.citation.title | IEEE Access | pt_PT |
| oaire.citation.volume | 10 | pt_PT |
| oaire.fundingStream | CEEC IND 2017 | |
| oaire.fundingStream | 6817 - DCRRNI ID | |
| person.familyName | Faria | |
| person.familyName | Vale | |
| person.givenName | Pedro | |
| person.givenName | Zita | |
| person.identifier | 632184 | |
| person.identifier.ciencia-id | B212-2309-F9C3 | |
| person.identifier.ciencia-id | 6F19-CB63-C8A8 | |
| person.identifier.ciencia-id | 721B-B0EB-7141 | |
| person.identifier.orcid | 0000-0002-5982-8342 | |
| person.identifier.orcid | 0000-0002-8597-3383 | |
| person.identifier.orcid | 0000-0002-4560-9544 | |
| person.identifier.rid | A-5824-2012 | |
| person.identifier.scopus-author-id | 7004115775 | |
| project.funder.identifier | http://doi.org/10.13039/501100001871 | |
| project.funder.identifier | http://doi.org/10.13039/501100001871 | |
| project.funder.name | Fundação para a Ciência e a Tecnologia | |
| project.funder.name | Fundação para a Ciência e a Tecnologia | |
| rcaap.rights | openAccess | pt_PT |
| rcaap.type | article | pt_PT |
| relation.isAuthorOfPublication | 35e6a4ab-f644-4bc5-b6fc-9fd89c23d6c6 | |
| relation.isAuthorOfPublication | eaac2304-a007-4531-8398-ee9f426c2f52 | |
| relation.isAuthorOfPublication | ff1df02d-0c0f-4db1-bf7d-78863a99420b | |
| relation.isAuthorOfPublication.latestForDiscovery | 35e6a4ab-f644-4bc5-b6fc-9fd89c23d6c6 | |
| relation.isProjectOfPublication | e9f5cdee-c0fb-4e2d-81bf-9316a3752526 | |
| relation.isProjectOfPublication | db3e2edb-b8af-487a-b76a-f6790ac2d86e | |
| relation.isProjectOfPublication.latestForDiscovery | db3e2edb-b8af-487a-b76a-f6790ac2d86e |