Spatial-Temporal Graph Convolutional-Based Recurrent Network for Electric Vehicle Charging Stations Demand Forecasting in Energy Market
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Hyung Joon | - |
dc.contributor.author | Kim, Mun Kyeom | - |
dc.date.accessioned | 2024-07-17T03:00:33Z | - |
dc.date.available | 2024-07-17T03:00:33Z | - |
dc.date.issued | 2024-07 | - |
dc.identifier.issn | 1949-3053 | - |
dc.identifier.issn | 1949-3061 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/74855 | - |
dc.description.abstract | The increasing adoption of electric vehicles has led to new and unpredictable load conditions for electric vehicle charging stations (EVCSs), making charging demand forecasting important to the profitable deployment of EVCSs. Although existing spatial-temporal forecasting models have made significant progress, they ignore the realistic topologies of EVCS networks and the influence of external interference on charging demand. Moreover, limited research exists on developing forecasting models from the perspective of EVCSs participating in the energy market. This paper proposes a novel parallel-structured spatio-temporal mutual residual graph convolution-combined bi-long short-term memory for predicting the charging demand of EVCSs. First, a new mutual adjacency matrix considering both the static and dynamic attributes of EVCSs is constructed. This matrix is then combined with graph convolution and residual blocks to capture multi-level spatial dependencies and map relations between nodes and external factors. Second, to address temporal dependencies, CBi-LSTM combining Bi-LSTM with an additional predictor that considers day-type tendency features is developed. Finally, a parallel structure is adopted to obtain the final prediction results and preserve the integrity of spatiotemporal dependencies. Case studies validated the performance of the proposed model, which demonstrated high forecasting accuracy and the potential for profitable application in the energy market. IEEE | - |
dc.format.extent | 15 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Spatial-Temporal Graph Convolutional-Based Recurrent Network for Electric Vehicle Charging Stations Demand Forecasting in Energy Market | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/TSG.2024.3368419 | - |
dc.identifier.bibliographicCitation | IEEE Transactions on Smart Grid, v.15, no.4, pp 3979 - 3993 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.wosid | 001252808400031 | - |
dc.identifier.scopusid | 2-s2.0-85186984831 | - |
dc.citation.endPage | 3993 | - |
dc.citation.number | 4 | - |
dc.citation.startPage | 3979 | - |
dc.citation.title | IEEE Transactions on Smart Grid | - |
dc.citation.volume | 15 | - |
dc.type.docType | Article | - |
dc.publisher.location | 미국 | - |
dc.subject.keywordAuthor | Biological system modeling | - |
dc.subject.keywordAuthor | Correlation | - |
dc.subject.keywordAuthor | Data models | - |
dc.subject.keywordAuthor | deep learning | - |
dc.subject.keywordAuthor | Demand forecasting | - |
dc.subject.keywordAuthor | Electric vehicle charging | - |
dc.subject.keywordAuthor | Electric vehicle charging station | - |
dc.subject.keywordAuthor | energy market | - |
dc.subject.keywordAuthor | forecasting | - |
dc.subject.keywordAuthor | graph convolution | - |
dc.subject.keywordAuthor | Load modeling | - |
dc.subject.keywordAuthor | Predictive models | - |
dc.subject.keywordAuthor | spatial-temporal | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang University All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.