Ensemble machine learning-based algorithm for electric vehicle user behavior prediction

[Display omitted] •Real electric vehicle charging data from 252 users were analyzed.•Defining the data entropy/sparsity ratio (R) as an indicator for predicting algorithm selection.•Exploiting the benefit of using diffusion-based kernel density estimator (DKDE) for prediction with high R data.•Reduc...

Full description

Saved in:

Bibliographic Details
Published in:	Applied energy Vol. 254; p. 113732
Main Authors:	Chung, Yu-Wei, Khaki, Behnam, Li, Tianyi, Chu, Chicheng, Gadh, Rajit
Format:	Journal Article
Language:	English
Published:	Elsevier Ltd 15.11.2019
Subjects:	algorithms artificial intelligence cost effectiveness Data entropy Data sparsity electric vehicles energy entropy EV user behavior prediction Kernel density estimator Machcine learning mathematical models prediction regression analysis variance Machcine learning Kernel density estimator Data sparsity Data entropy EV user behavior prediction
ISSN:	0306-2619, 1872-9118
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	[Display omitted] •Real electric vehicle charging data from 252 users were analyzed.•Defining the data entropy/sparsity ratio (R) as an indicator for predicting algorithm selection.•Exploiting the benefit of using diffusion-based kernel density estimator (DKDE) for prediction with high R data.•Reducing at least 10% of prediction error compared to a single predicting algorithm. This research investigates electric vehicle (EV) charging behavior and aims to find the best method for its prediction in order to optimize the EV charging schedule. This paper discusses several commonly used machine learning algorithms to predict charging behavior, including stay duration and energy consumption based on historical charging records. It is noted that prediction error increases along with the rise of data entropy or the decrease of data sparsity. Thus, this paper accounts for both indicators by defining the entropy/sparsity ratio (R). When R is low, support vector regression (SVR) and random forest (RF) regression show better accuracy for stay duration and energy consumption predictions, respectively. While R is high, a diffusion-based kernel density estimator (DKDE) performs better for both predictions. The three methods are assembled as the proposed Ensemble Predicting Algorithm (EPA) to improve predicting performance by decreasing 11% of the duration and 22% of the energy consumption prediction errors. The prediction results are then applied to an optimal EV charging scheduling algorithm to minimize load variance while reducing the EV charging cost. A numerical simulation using real charging data is conducted to show the effectiveness of improved predictions and EV load management. The results show that the charging scheduling combined with EPA prediction can reduce 27% of peak load, 10% of load variation, and 4% cost reduction, compared to uncoordinated charging.
AbstractList	This research investigates electric vehicle (EV) charging behavior and aims to find the best method for its prediction in order to optimize the EV charging schedule. This paper discusses several commonly used machine learning algorithms to predict charging behavior, including stay duration and energy consumption based on historical charging records. It is noted that prediction error increases along with the rise of data entropy or the decrease of data sparsity. Thus, this paper accounts for both indicators by defining the entropy/sparsity ratio (R). When R is low, support vector regression (SVR) and random forest (RF) regression show better accuracy for stay duration and energy consumption predictions, respectively. While R is high, a diffusion-based kernel density estimator (DKDE) performs better for both predictions. The three methods are assembled as the proposed Ensemble Predicting Algorithm (EPA) to improve predicting performance by decreasing 11% of the duration and 22% of the energy consumption prediction errors. The prediction results are then applied to an optimal EV charging scheduling algorithm to minimize load variance while reducing the EV charging cost. A numerical simulation using real charging data is conducted to show the effectiveness of improved predictions and EV load management. The results show that the charging scheduling combined with EPA prediction can reduce 27% of peak load, 10% of load variation, and 4 % cost reduction, compared to uncoordinated charging. [Display omitted] •Real electric vehicle charging data from 252 users were analyzed.•Defining the data entropy/sparsity ratio (R) as an indicator for predicting algorithm selection.•Exploiting the benefit of using diffusion-based kernel density estimator (DKDE) for prediction with high R data.•Reducing at least 10% of prediction error compared to a single predicting algorithm. This research investigates electric vehicle (EV) charging behavior and aims to find the best method for its prediction in order to optimize the EV charging schedule. This paper discusses several commonly used machine learning algorithms to predict charging behavior, including stay duration and energy consumption based on historical charging records. It is noted that prediction error increases along with the rise of data entropy or the decrease of data sparsity. Thus, this paper accounts for both indicators by defining the entropy/sparsity ratio (R). When R is low, support vector regression (SVR) and random forest (RF) regression show better accuracy for stay duration and energy consumption predictions, respectively. While R is high, a diffusion-based kernel density estimator (DKDE) performs better for both predictions. The three methods are assembled as the proposed Ensemble Predicting Algorithm (EPA) to improve predicting performance by decreasing 11% of the duration and 22% of the energy consumption prediction errors. The prediction results are then applied to an optimal EV charging scheduling algorithm to minimize load variance while reducing the EV charging cost. A numerical simulation using real charging data is conducted to show the effectiveness of improved predictions and EV load management. The results show that the charging scheduling combined with EPA prediction can reduce 27% of peak load, 10% of load variation, and 4% cost reduction, compared to uncoordinated charging.
ArticleNumber	113732
Author	Gadh, Rajit Chu, Chicheng Chung, Yu-Wei Li, Tianyi Khaki, Behnam
Author_xml	– sequence: 1 givenname: Yu-Wei surname: Chung fullname: Chung, Yu-Wei email: ywchung@ucla.edu – sequence: 2 givenname: Behnam surname: Khaki fullname: Khaki, Behnam email: behnamkhaki@ucla.edu – sequence: 3 givenname: Tianyi surname: Li fullname: Li, Tianyi email: tianyi3gli@ucla.edu – sequence: 4 givenname: Chicheng surname: Chu fullname: Chu, Chicheng email: peterchu@ucla.edu – sequence: 5 givenname: Rajit surname: Gadh fullname: Gadh, Rajit email: gadh@ucla.edu
BookMark	eNqFkD1rwzAQhkVJoUnav1A8drGrj1iWoUNLSD8g0KWlo5Clc6xgy6nkBPLvq-B26ZLp4O59jrtnhiaud4DQLcEZwYTfbzO1Awd-c8woJmVGCCsYvUBTIgqaloSICZpihnlKOSmv0CyELcaYEoqn6GvlAnRVC0mndGMdJC0o76zbpJUKYBLVbnpvh6ZL6t4n0IIevNXJARqrI7UP4JMKGnWwcbzzYKwebO-u0WWt2gA3v3WOPp9XH8vXdP3-8rZ8WqeaLfIhrRes1orUipZ5xYWpNTaA4_0qNk0papIzoQ1jOj6Vg9CVEoRjk1eGAV9UbI7uxr0733_vIQyys0FD2yoH_T5IynBOeEFFEaMPY1T7PgQPtdR2UKdjB69sKwmWJ59yK_98ypNPOfqMOP-H77ztlD-eBx9HEKKHgwUvg7bgdFTlo01pentuxQ-aQJg0
CitedBy_id	crossref_primary_10_1016_j_est_2022_105468 crossref_primary_10_3390_wevj12040263 crossref_primary_10_1016_j_engappai_2024_108789 crossref_primary_10_1109_TIV_2024_3432075 crossref_primary_10_1109_TIV_2023_3328458 crossref_primary_10_1016_j_ecmx_2025_100978 crossref_primary_10_1016_j_iot_2024_101344 crossref_primary_10_1016_j_rineng_2025_105104 crossref_primary_10_1016_j_apenergy_2023_121334 crossref_primary_10_1016_j_est_2024_112151 crossref_primary_10_1051_e3sconf_202456402009 crossref_primary_10_1080_00207721_2023_2268234 crossref_primary_10_3390_en15218115 crossref_primary_10_1016_j_energy_2025_136683 crossref_primary_10_1007_s42835_025_02459_0 crossref_primary_10_1111_coin_12333 crossref_primary_10_3390_en17246457 crossref_primary_10_1080_21680566_2023_2248400 crossref_primary_10_3390_en18061528 crossref_primary_10_3390_en13164231 crossref_primary_10_1109_TSTE_2024_3497659 crossref_primary_10_3390_wevj15040150 crossref_primary_10_1016_j_apenergy_2025_125302 crossref_primary_10_1109_TITS_2023_3286012 crossref_primary_10_1007_s41939_024_00457_9 crossref_primary_10_1109_ACCESS_2023_3334620 crossref_primary_10_1155_2022_4372168 crossref_primary_10_3390_app14073092 crossref_primary_10_1016_j_apenergy_2021_118456 crossref_primary_10_3390_en17071651 crossref_primary_10_1109_JIOT_2024_3511961 crossref_primary_10_1111_grow_12587 crossref_primary_10_1016_j_renene_2025_124141 crossref_primary_10_1016_j_enconman_2025_119965 crossref_primary_10_1016_j_apenergy_2024_123059 crossref_primary_10_3390_su151813315 crossref_primary_10_1016_j_est_2022_104917 crossref_primary_10_1016_j_est_2024_113021 crossref_primary_10_3389_fenrg_2022_773440 crossref_primary_10_1007_s10489_020_02160_x crossref_primary_10_1139_cjfr_2020_0506 crossref_primary_10_1007_s13042_025_02643_8 crossref_primary_10_3390_electronics12092047 crossref_primary_10_1016_j_chb_2024_108245 crossref_primary_10_1049_gtd2_12494 crossref_primary_10_3390_s22072752 crossref_primary_10_3390_electronics12020373 crossref_primary_10_1016_j_tbs_2022_11_006 crossref_primary_10_1109_TIA_2022_3215978 crossref_primary_10_1002_widm_1539 crossref_primary_10_1016_j_renene_2024_121243 crossref_primary_10_1016_j_apenergy_2023_121884 crossref_primary_10_1016_j_epsr_2022_107913 crossref_primary_10_1109_TIA_2024_3456753 crossref_primary_10_1016_j_apenergy_2023_120798 crossref_primary_10_3390_en16052385 crossref_primary_10_3390_wevj15020063 crossref_primary_10_1007_s10479_025_06696_4 crossref_primary_10_3390_en16010462 crossref_primary_10_3390_en17040925 crossref_primary_10_1016_j_energy_2022_126274 crossref_primary_10_1016_j_apenergy_2024_125174 crossref_primary_10_1109_ACCESS_2021_3071180 crossref_primary_10_3389_fdata_2024_1402384 crossref_primary_10_1016_j_energy_2022_124642 crossref_primary_10_3390_ma12244150 crossref_primary_10_1109_TTE_2024_3438448 crossref_primary_10_1016_j_trc_2023_104149 crossref_primary_10_1016_j_apenergy_2024_124925 crossref_primary_10_1016_j_energy_2025_134582 crossref_primary_10_1007_s40747_025_01988_5 crossref_primary_10_32628_CSEIT251112280 crossref_primary_10_3390_vehicles6040101 crossref_primary_10_1080_15472450_2021_2010053 crossref_primary_10_1109_TSG_2022_3150074 crossref_primary_10_1016_j_segan_2022_100932 crossref_primary_10_1016_j_apenergy_2025_126673 crossref_primary_10_3390_ijgi9040272 crossref_primary_10_1016_j_ijepes_2025_110690 crossref_primary_10_1016_j_epsr_2023_110077 crossref_primary_10_1016_j_apenergy_2024_123544 crossref_primary_10_1109_ACCESS_2024_3405959 crossref_primary_10_1007_s11831_024_10214_3 crossref_primary_10_1016_j_segan_2024_101463 crossref_primary_10_1016_j_scs_2024_105453 crossref_primary_10_3390_en15186575 crossref_primary_10_1016_j_ijepes_2022_108486 crossref_primary_10_3390_math8101799 crossref_primary_10_1115_1_4068619 crossref_primary_10_1109_ACCESS_2021_3103119 crossref_primary_10_1016_j_est_2022_106294 crossref_primary_10_1155_2022_6819525 crossref_primary_10_1007_s11227_024_06820_4 crossref_primary_10_1016_j_joule_2021_07_012 crossref_primary_10_3390_en18174779 crossref_primary_10_3390_en14041090 crossref_primary_10_1155_2021_4216215 crossref_primary_10_1016_j_est_2023_108672 crossref_primary_10_1016_j_apenergy_2020_115237 crossref_primary_10_1038_s41558_022_01489_0 crossref_primary_10_1002_ente_202300744 crossref_primary_10_1016_j_segan_2025_101945 crossref_primary_10_1016_j_energy_2022_124160 crossref_primary_10_1016_j_segan_2023_101224 crossref_primary_10_1109_ACCESS_2020_3023388 crossref_primary_10_1145_3609508 crossref_primary_10_1007_s11116_024_10574_6 crossref_primary_10_1016_j_est_2023_107577 crossref_primary_10_1109_ACCESS_2022_3180493 crossref_primary_10_1007_s42979_022_01233_7
Cites_doi	10.1016/j.apenergy.2014.03.078 10.1016/j.apenergy.2016.12.139 10.1109/PMAPS.2018.8440360 10.1016/j.apenergy.2010.12.015 10.1016/j.apenergy.2015.10.151 10.1109/TPWRS.2012.2210288 10.1109/TII.2014.2374993 10.1109/PESGM40551.2019.8973928 10.1016/j.apenergy.2013.10.006 10.1109/PESGM.2018.8585744 10.1214/10-AOS799 10.1016/j.apenergy.2015.10.184 10.1016/j.apenergy.2019.03.008 10.1016/j.apenergy.2015.05.057 10.1016/j.apenergy.2012.06.052 10.1016/j.apenergy.2014.09.091 10.1080/00031305.1992.10475879 10.1016/j.apenergy.2018.09.139 10.1016/j.epsr.2016.06.003 10.1016/j.apenergy.2014.03.003 10.1023/B:STCO.0000035301.49549.88 10.1016/j.apenergy.2014.08.116
ContentType	Journal Article
Copyright	2019 Elsevier Ltd
Copyright_xml	– notice: 2019 Elsevier Ltd
DBID	AAYXX CITATION 7S9 L.6
DOI	10.1016/j.apenergy.2019.113732
DatabaseName	CrossRef AGRICOLA AGRICOLA - Academic
DatabaseTitle	CrossRef AGRICOLA AGRICOLA - Academic
DatabaseTitleList	AGRICOLA
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Environmental Sciences
EISSN	1872-9118
ExternalDocumentID	10_1016_j_apenergy_2019_113732 S0306261919314199
GroupedDBID	--K --M .~1 0R~ 1B1 1~. 1~5 23M 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAHCO AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AARJD AAXUO ABJNI ABMAC ABYKQ ACDAQ ACGFS ACRLP ADBBV ADEZE ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHIDL AHJVU AIEXJ AIKHN AITUG AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AXJTR BELTK BJAXD BKOJK BLXMC CS3 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 FDB FIRID FNPLU FYGXN G-Q GBLVA IHE J1W JARJE JJJVA KOM LY6 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 RIG ROL RPZ SDF SDG SES SPC SPCBC SSR SST SSZ T5K TN5 ~02 ~G- 9DU AAHBH AAQXK AATTM AAXKI AAYWO AAYXX ABEFU ABFNM ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADMUD ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS FEDTE FGOYB G-2 HVGLF HZ~ R2- SAC SEW WUQ ZY4 ~HD 7S9 L.6
ID	FETCH-LOGICAL-c345t-f43fca1fa295b68dfc0de0373aa1fd98f1538cd33c1375e8cba8160d5bd3e64b3
ISICitedReferencesCount	141
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000497974600116&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0306-2619
IngestDate	Wed Oct 01 14:48:31 EDT 2025 Tue Nov 18 21:19:31 EST 2025 Sat Nov 29 07:20:40 EST 2025 Fri Feb 23 02:30:28 EST 2024
IsPeerReviewed	true
IsScholarly	true
Keywords	Machcine learning Kernel density estimator Data sparsity Data entropy EV user behavior prediction
Language	English
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c345t-f43fca1fa295b68dfc0de0373aa1fd98f1538cd33c1375e8cba8160d5bd3e64b3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
PQID	2305167287
PQPubID	24069
ParticipantIDs	proquest_miscellaneous_2305167287 crossref_citationtrail_10_1016_j_apenergy_2019_113732 crossref_primary_10_1016_j_apenergy_2019_113732 elsevier_sciencedirect_doi_10_1016_j_apenergy_2019_113732
PublicationCentury	2000
PublicationDate	2019-11-15
PublicationDateYYYYMMDD	2019-11-15
PublicationDate_xml	– month: 11 year: 2019 text: 2019-11-15 day: 15
PublicationDecade	2010
PublicationTitle	Applied energy
PublicationYear	2019
Publisher	Elsevier Ltd
Publisher_xml	– name: Elsevier Ltd
References	Eatechnology.com, My electric avenue data [online]; 2016 [accessed: 03.01.2018] URL Khaki B, Chung YW, Chu C, Gadh R. Nonparametric user behavior prediction for distributed EV charging scheduling. In: 2018 IEEE power and energy society general meeting conf (PESGM 2018); 2018. Loveday S. Plug-In electric vehicle sales report card; June 2019 [accessed: 07.25.2019] Xiong, Wang, Cheng Chu, Gadh (b0065) 2018; 231 Cristopher (b0165) 2016 Khaki B, Chung YW, Chu C, Gadh R. Hierarchical distributed EV charging scheduling in distribution grids. In: 2019 IEEE power and energy society general meeting conf (PESGM 2019); 2019. Mu, Wu, Jenkins, Jia, Wang (b0015) 2014; 114 Kristoffersen, Capion, Meibom (b0040) 2011; 88 Keyhani (b0180) 2016 Khaki, Chu, Gadh (b0170) 2019; 241 Amini, Kargarian, Karabasoglu (b0080) 2016; 11 Chung YW, Khaki B, Chu C, Gadh R. Electric vehicle user behavior prediction using hybrid kernel density estimator. In: 2018 IEEE international conference on probabilistic methods applied to power systems (PMAPS 2018); 2018. p. 1–6. Gennaro, Paffumi, Scholz, Martini (b0045) 2014; 124 Majidpour, Qiu, Chu, Pota, Gadh (b0105) 2016; 163 Veloz. Sales dashboard. [accessed: 07.25.2019] Johnson T. Americans spend an average of 17,600 minutes driving each year [accessed: 11.10.2018] Smart Grid Energy Research Center (SMERC), UCLA, Smart grid project - smart EV charging station [accessed: 03.01.2018] Wang, Shi, Wang, Chu, Gadh (b0115) 2017; 190 Vapnik (b0150) 1995 Wang, Zhang, Ouyang (b0055) 2015; 157 Majidpour, Qiu, Chu, Gadh, Pota (b0075) 2015; 140 Gan, Topcu, Low (b0035) 2013; 28 Silverman (b0125) 1998 Buitinck L, Louppe G, Blondel M, Pedregosa F, Mueller A, Grisel O, et al. API design for machine learning software: experiences from the scikit-learn project. In: ECML PKDD workshop: languages for data mining and machine learning; 2013. p. 108–22. Wang, Hu, Qiu, Chu, Gadh (b0085) 2015 Majidpour, Qiu, Chu, Gadh, Pota (b0095) 2014 Altman (b0160) 1992; 46 Xydas, Marmaras, Cipcigan, Jenkins, Carroll, Barker (b0090) 2016; 162 . Smola AJ, Schölkopf B. A tutorial on support vector regression. Tech rep, Statistics and Computing; 2003. Botev, Grotowski, Kroese (b0130) 2010; 38 Foley, Tyther, Calnan, Gallachóir (b0025) 2013; 101 Harris, Webber (b0050) 2014; 126 Xu, Hu, Song, Zhao, Zhang (b0100) 2014; 136 Wang, Wang, Nazaripouya, Qiu, Chu, Gadh (b0110) 2017; 4 Wang, Huang, Wang, Nazaripouya, Qiu, Chu (b0120) 2016 Salah, Ilg, Flath, Basse, van Dinther (b0020) 2015; 137 California Independent System Operator (CAISO). Locational marginal price [Online]; 2018 [accessed: 01.05.2018] Open Charge Alliance, Global Platform for Open Protocols. [accessed: 07.25.2019] Xiong (10.1016/j.apenergy.2019.113732_b0065) 2018; 231 Amini (10.1016/j.apenergy.2019.113732_b0080) 2016; 11 Xu (10.1016/j.apenergy.2019.113732_b0100) 2014; 136 Wang (10.1016/j.apenergy.2019.113732_b0110) 2017; 4 Xydas (10.1016/j.apenergy.2019.113732_b0090) 2016; 162 Botev (10.1016/j.apenergy.2019.113732_b0130) 2010; 38 Vapnik (10.1016/j.apenergy.2019.113732_b0150) 1995 Silverman (10.1016/j.apenergy.2019.113732_b0125) 1998 Harris (10.1016/j.apenergy.2019.113732_b0050) 2014; 126 Foley (10.1016/j.apenergy.2019.113732_b0025) 2013; 101 Gennaro (10.1016/j.apenergy.2019.113732_b0045) 2014; 124 Keyhani (10.1016/j.apenergy.2019.113732_b0180) 2016 Salah (10.1016/j.apenergy.2019.113732_b0020) 2015; 137 Cristopher (10.1016/j.apenergy.2019.113732_b0165) 2016 10.1016/j.apenergy.2019.113732_b0145 10.1016/j.apenergy.2019.113732_b0005 10.1016/j.apenergy.2019.113732_b0140 10.1016/j.apenergy.2019.113732_b0185 10.1016/j.apenergy.2019.113732_b0060 Majidpour (10.1016/j.apenergy.2019.113732_b0075) 2015; 140 Wang (10.1016/j.apenergy.2019.113732_b0055) 2015; 157 Khaki (10.1016/j.apenergy.2019.113732_b0170) 2019; 241 10.1016/j.apenergy.2019.113732_b0190 Majidpour (10.1016/j.apenergy.2019.113732_b0095) 2014 Wang (10.1016/j.apenergy.2019.113732_b0115) 2017; 190 Majidpour (10.1016/j.apenergy.2019.113732_b0105) 2016; 163 Wang (10.1016/j.apenergy.2019.113732_b0120) 2016 Gan (10.1016/j.apenergy.2019.113732_b0035) 2013; 28 Wang (10.1016/j.apenergy.2019.113732_b0085) 2015 Mu (10.1016/j.apenergy.2019.113732_b0015) 2014; 114 10.1016/j.apenergy.2019.113732_b0155 10.1016/j.apenergy.2019.113732_b0135 Kristoffersen (10.1016/j.apenergy.2019.113732_b0040) 2011; 88 10.1016/j.apenergy.2019.113732_b0175 10.1016/j.apenergy.2019.113732_b0070 Altman (10.1016/j.apenergy.2019.113732_b0160) 1992; 46 10.1016/j.apenergy.2019.113732_b0010 10.1016/j.apenergy.2019.113732_b0030
References_xml	– year: 2016 ident: b0180 article-title: Design of smart power grid renewable energy systems – volume: 241 start-page: 461 year: 2019 end-page: 471 ident: b0170 article-title: Hierarchical distributed framework for ev charging scheduling using exchange problem publication-title: Appl Energy – volume: 46 start-page: 175 year: 1992 end-page: 185 ident: b0160 article-title: An introduction to kernel and nearest-neighbor nonparametric regression publication-title: Am Stat – volume: 4 start-page: 52 year: 2017 end-page: 63 ident: b0110 article-title: Predictive scheduling framework for electric vehicles with uncertainties of user behaviors publication-title: IEEE Internet Things J – volume: 88 start-page: 1940 year: 2011 end-page: 1948 ident: b0040 article-title: Optimal charging of electric drive vehicles in a market environment publication-title: Appl Energy – reference: Smola AJ, Schölkopf B. A tutorial on support vector regression. Tech rep, Statistics and Computing; 2003. – volume: 114 start-page: 456 year: 2014 end-page: 465 ident: b0015 article-title: A spatial–temporal model for grid impact analysis of plug-in electric vehicles publication-title: Appl Energy – reference: Smart Grid Energy Research Center (SMERC), UCLA, Smart grid project - smart EV charging station [accessed: 03.01.2018] – reference: Khaki B, Chung YW, Chu C, Gadh R. Hierarchical distributed EV charging scheduling in distribution grids. In: 2019 IEEE power and energy society general meeting conf (PESGM 2019); 2019. – reference: Eatechnology.com, My electric avenue data [online]; 2016 [accessed: 03.01.2018] URL – year: 1998 ident: b0125 article-title: Density estimation for statistics and data analysis – reference: Khaki B, Chung YW, Chu C, Gadh R. Nonparametric user behavior prediction for distributed EV charging scheduling. In: 2018 IEEE power and energy society general meeting conf (PESGM 2018); 2018. – reference: Johnson T. Americans spend an average of 17,600 minutes driving each year [accessed: 11.10.2018] – volume: 137 start-page: 88 year: 2015 end-page: 96 ident: b0020 article-title: Impact of electric vehicles on distribution substations: a Swiss case study publication-title: Appl Energy – volume: 163 start-page: 134 year: 2016 end-page: 141 ident: b0105 article-title: Forecasting the EV charging load based on customer profile or station measurement? publication-title: Appl Energy – start-page: 1 year: 2016 end-page: 5 ident: b0120 article-title: Predictive scheduling for Electric Vehicles considering uncertainty of load and user behaviors publication-title: 2016 IEEE/PES transmission and distribution conference and exposition (T&D 2016) – reference: Open Charge Alliance, Global Platform for Open Protocols. [accessed: 07.25.2019] – start-page: 1 year: 2015 end-page: 5 ident: b0085 article-title: EV charging algorithm implementation with user price preference publication-title: IEEE power energy society innovative smart grid technologies conference (ISGT), 2015 – volume: 28 start-page: 940 year: 2013 end-page: 951 ident: b0035 article-title: Optimal decentralized protocol for electric vehicle charging publication-title: IEEE Trans Power Syst – volume: 162 start-page: 763 year: 2016 end-page: 771 ident: b0090 article-title: A data-driven approach for characterising the charging demand of electric vehicles: a UK case study publication-title: Appl Energy – start-page: 1035 year: 2014 end-page: 1040 ident: b0095 article-title: A novel forecasting algorithm for electric vehicle charging stations publication-title: International conference on connected vehicles and expo (ICCVE), 2014 – volume: 126 start-page: 172 year: 2014 end-page: 181 ident: b0050 article-title: An empirically-validated methodology to simulate electricity demand for electric vehicle charging publication-title: Appl Energy – reference: Veloz. Sales dashboard. [accessed: 07.25.2019] – year: 1995 ident: b0150 article-title: The nature of statistical learning theory – volume: 136 start-page: 582 year: 2014 end-page: 589 ident: b0100 article-title: Coordination of PEVs charging across multiple aggregators publication-title: Appl Energy – reference: Chung YW, Khaki B, Chu C, Gadh R. Electric vehicle user behavior prediction using hybrid kernel density estimator. In: 2018 IEEE international conference on probabilistic methods applied to power systems (PMAPS 2018); 2018. p. 1–6. – reference: Loveday S. Plug-In electric vehicle sales report card; June 2019 [accessed: 07.25.2019] – volume: 124 start-page: 94 year: 2014 end-page: 116 ident: b0045 article-title: GIS-driven analysis of e-mobility in urban areas: an evaluation of the impact on the electric energy grid publication-title: Appl Energy – reference: California Independent System Operator (CAISO). Locational marginal price [Online]; 2018 [accessed: 01.05.2018] – reference: . – volume: 11 start-page: 378 year: 2016 end-page: 390 ident: b0080 article-title: ARIMA-based decoupled time series forecasting of electric vehicle charging demand for stochastic power system operation publication-title: Electric Power Syst Res – volume: 101 start-page: 93 year: 2013 end-page: 102 ident: b0025 article-title: Impacts of electric vehicle charging under electricity market operations publication-title: Appl Energy – year: 2016 ident: b0165 article-title: Pattern recognition and machine learning – volume: 38 start-page: 2916 year: 2010 end-page: 2957 ident: b0130 article-title: Kernel density estimation via diffusion publication-title: Ann Statist – reference: Buitinck L, Louppe G, Blondel M, Pedregosa F, Mueller A, Grisel O, et al. API design for machine learning software: experiences from the scikit-learn project. In: ECML PKDD workshop: languages for data mining and machine learning; 2013. p. 108–22. – volume: 231 start-page: 481 year: 2018 end-page: 493 ident: b0065 article-title: Vehicle grid integration for demand response with mixture user model and decentralized optimization publication-title: Appl Energy – volume: 157 start-page: 710 year: 2015 end-page: 719 ident: b0055 article-title: Energy consumption of electric vehicles based on real-world driving patterns: a case study of Beijing publication-title: Appl Energy – volume: 190 start-page: 1289 year: 2017 end-page: 1301 ident: b0115 article-title: Optimal operation of stationary and mobile batteries in distribution grids publication-title: Appl Energy – volume: 140 start-page: 242 year: 2015 end-page: 250 ident: b0075 article-title: Fast prediction for sparse time series: demand forecast of EV charging stations for cell phone applications publication-title: IEEE Trans Ind Inform – volume: 126 start-page: 172 year: 2014 ident: 10.1016/j.apenergy.2019.113732_b0050 article-title: An empirically-validated methodology to simulate electricity demand for electric vehicle charging publication-title: Appl Energy doi: 10.1016/j.apenergy.2014.03.078 – volume: 190 start-page: 1289 year: 2017 ident: 10.1016/j.apenergy.2019.113732_b0115 article-title: Optimal operation of stationary and mobile batteries in distribution grids publication-title: Appl Energy doi: 10.1016/j.apenergy.2016.12.139 – year: 1998 ident: 10.1016/j.apenergy.2019.113732_b0125 – start-page: 1 year: 2015 ident: 10.1016/j.apenergy.2019.113732_b0085 article-title: EV charging algorithm implementation with user price preference – volume: 4 start-page: 52 issue: 1 year: 2017 ident: 10.1016/j.apenergy.2019.113732_b0110 article-title: Predictive scheduling framework for electric vehicles with uncertainties of user behaviors publication-title: IEEE Internet Things J – ident: 10.1016/j.apenergy.2019.113732_b0140 doi: 10.1109/PMAPS.2018.8440360 – volume: 88 start-page: 1940 issue: 5 year: 2011 ident: 10.1016/j.apenergy.2019.113732_b0040 article-title: Optimal charging of electric drive vehicles in a market environment publication-title: Appl Energy doi: 10.1016/j.apenergy.2010.12.015 – volume: 162 start-page: 763 year: 2016 ident: 10.1016/j.apenergy.2019.113732_b0090 article-title: A data-driven approach for characterising the charging demand of electric vehicles: a UK case study publication-title: Appl Energy doi: 10.1016/j.apenergy.2015.10.151 – volume: 28 start-page: 940 issue: 2 year: 2013 ident: 10.1016/j.apenergy.2019.113732_b0035 article-title: Optimal decentralized protocol for electric vehicle charging publication-title: IEEE Trans Power Syst doi: 10.1109/TPWRS.2012.2210288 – volume: 140 start-page: 242 issue: 1 year: 2015 ident: 10.1016/j.apenergy.2019.113732_b0075 article-title: Fast prediction for sparse time series: demand forecast of EV charging stations for cell phone applications publication-title: IEEE Trans Ind Inform doi: 10.1109/TII.2014.2374993 – ident: 10.1016/j.apenergy.2019.113732_b0185 doi: 10.1109/PESGM40551.2019.8973928 – volume: 114 start-page: 456 year: 2014 ident: 10.1016/j.apenergy.2019.113732_b0015 article-title: A spatial–temporal model for grid impact analysis of plug-in electric vehicles publication-title: Appl Energy doi: 10.1016/j.apenergy.2013.10.006 – year: 2016 ident: 10.1016/j.apenergy.2019.113732_b0180 – ident: 10.1016/j.apenergy.2019.113732_b0135 doi: 10.1109/PESGM.2018.8585744 – volume: 38 start-page: 2916 issue: 5 year: 2010 ident: 10.1016/j.apenergy.2019.113732_b0130 article-title: Kernel density estimation via diffusion publication-title: Ann Statist doi: 10.1214/10-AOS799 – volume: 163 start-page: 134 year: 2016 ident: 10.1016/j.apenergy.2019.113732_b0105 article-title: Forecasting the EV charging load based on customer profile or station measurement? publication-title: Appl Energy doi: 10.1016/j.apenergy.2015.10.184 – volume: 241 start-page: 461 year: 2019 ident: 10.1016/j.apenergy.2019.113732_b0170 article-title: Hierarchical distributed framework for ev charging scheduling using exchange problem publication-title: Appl Energy doi: 10.1016/j.apenergy.2019.03.008 – volume: 157 start-page: 710 year: 2015 ident: 10.1016/j.apenergy.2019.113732_b0055 article-title: Energy consumption of electric vehicles based on real-world driving patterns: a case study of Beijing publication-title: Appl Energy doi: 10.1016/j.apenergy.2015.05.057 – ident: 10.1016/j.apenergy.2019.113732_b0030 – ident: 10.1016/j.apenergy.2019.113732_b0145 – year: 2016 ident: 10.1016/j.apenergy.2019.113732_b0165 – ident: 10.1016/j.apenergy.2019.113732_b0070 – volume: 101 start-page: 93 year: 2013 ident: 10.1016/j.apenergy.2019.113732_b0025 article-title: Impacts of electric vehicle charging under electricity market operations publication-title: Appl Energy doi: 10.1016/j.apenergy.2012.06.052 – start-page: 1 year: 2016 ident: 10.1016/j.apenergy.2019.113732_b0120 article-title: Predictive scheduling for Electric Vehicles considering uncertainty of load and user behaviors – volume: 137 start-page: 88 year: 2015 ident: 10.1016/j.apenergy.2019.113732_b0020 article-title: Impact of electric vehicles on distribution substations: a Swiss case study publication-title: Appl Energy doi: 10.1016/j.apenergy.2014.09.091 – volume: 46 start-page: 175 issue: 3 year: 1992 ident: 10.1016/j.apenergy.2019.113732_b0160 article-title: An introduction to kernel and nearest-neighbor nonparametric regression publication-title: Am Stat doi: 10.1080/00031305.1992.10475879 – ident: 10.1016/j.apenergy.2019.113732_b0175 – volume: 231 start-page: 481 year: 2018 ident: 10.1016/j.apenergy.2019.113732_b0065 article-title: Vehicle grid integration for demand response with mixture user model and decentralized optimization publication-title: Appl Energy doi: 10.1016/j.apenergy.2018.09.139 – volume: 11 start-page: 378 year: 2016 ident: 10.1016/j.apenergy.2019.113732_b0080 article-title: ARIMA-based decoupled time series forecasting of electric vehicle charging demand for stochastic power system operation publication-title: Electric Power Syst Res doi: 10.1016/j.epsr.2016.06.003 – volume: 124 start-page: 94 year: 2014 ident: 10.1016/j.apenergy.2019.113732_b0045 article-title: GIS-driven analysis of e-mobility in urban areas: an evaluation of the impact on the electric energy grid publication-title: Appl Energy doi: 10.1016/j.apenergy.2014.03.003 – ident: 10.1016/j.apenergy.2019.113732_b0155 doi: 10.1023/B:STCO.0000035301.49549.88 – ident: 10.1016/j.apenergy.2019.113732_b0005 – volume: 136 start-page: 582 year: 2014 ident: 10.1016/j.apenergy.2019.113732_b0100 article-title: Coordination of PEVs charging across multiple aggregators publication-title: Appl Energy doi: 10.1016/j.apenergy.2014.08.116 – start-page: 1035 year: 2014 ident: 10.1016/j.apenergy.2019.113732_b0095 article-title: A novel forecasting algorithm for electric vehicle charging stations – ident: 10.1016/j.apenergy.2019.113732_b0190 – ident: 10.1016/j.apenergy.2019.113732_b0060 – year: 1995 ident: 10.1016/j.apenergy.2019.113732_b0150 – ident: 10.1016/j.apenergy.2019.113732_b0010
SSID	ssj0002120
Score	2.6487072
SecondaryResourceType	review_article
Snippet	[Display omitted] •Real electric vehicle charging data from 252 users were analyzed.•Defining the data entropy/sparsity ratio (R) as an indicator for... This research investigates electric vehicle (EV) charging behavior and aims to find the best method for its prediction in order to optimize the EV charging...
SourceID	proquest crossref elsevier
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	113732
SubjectTerms	algorithms artificial intelligence cost effectiveness Data entropy Data sparsity electric vehicles energy entropy EV user behavior prediction Kernel density estimator Machcine learning mathematical models prediction regression analysis variance
Title	Ensemble machine learning-based algorithm for electric vehicle user behavior prediction
URI	https://dx.doi.org/10.1016/j.apenergy.2019.113732 https://www.proquest.com/docview/2305167287
Volume	254
WOSCitedRecordID	wos000497974600116&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1872-9118 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002120 issn: 0306-2619 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwELeg4wEepjGYGIPJSLxVgSbOh_04UKeB0ITE0MpT5NiXNdOaVk077c_nHNtJx4cGQrxEkRXbie_nu_PlPgh5neL-j7liQViwIogB2j1XBAJSKKEUWpdtyvxP2ekpn0zEZ-eQ2bTlBLK65jc3YvFfSY1tSGwTOvsX5O4GxQa8R6LjFcmO1z8i_LhuYGbioWatnyT4whAXgZFYeiivLubLajWd2WzfbRmcSg2vYWpGGhqrRRe8b1II6Ep1xPPpap3qCm3gYO8h4BjHt3VwDlXHyqfSlsZ-B9NazjoPoMpCBZlRtTGCdQEw_qlOpDqLRChMaJ6NybRmMh8q0_slteFZozQwxzUreCy35VlkuC3fZMeRTSr9E2u3VobLN3JhP8645QlTkiZzBtLbabO_mAnNfKihhnEoxH2yFWWJ4AOydfRhPPnYyevIJe_0L7gRR_7r2X6nwvwgzFsN5WyHbLujBT2ykHhM7kG9Sx5tJJzcJXvjPq4RH3WMvXlCzj1qqEMNvY0a2qGGImqoRw11qKEGNdSjhvaoeUq-Ho_P3p8EruZGoFicrIIyZqWSYSkjkRQp16UaaRjhV0ts1IKXRkIqzZjCpUiAq0LyMB3ppNAM0rhge2RQz2t4RihLJAdUQPHBKC4jJSBEZTWGUKcyFpztk8QvY65cQnpTF-Uq956Hl7lf_twsf26Xf5-87fotbEqWO3sIT6XcKZZWYcwRXHf2feXJmiPnNb_TZA3zdZPj4T0J0yzi2fN_GP-APOz30AsyWC3X8JI8UNerqlkeOqx-B7O5sAQ
linkProvider	Elsevier
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Ensemble+machine+learning-based+algorithm+for+electric+vehicle+user+behavior+prediction&rft.jtitle=Applied+energy&rft.au=Chung%2C+Yu-Wei&rft.au=Khaki%2C+Behnam&rft.au=Li%2C+Tianyi&rft.au=Chu%2C+Chicheng&rft.date=2019-11-15&rft.pub=Elsevier+Ltd&rft.issn=0306-2619&rft.eissn=1872-9118&rft.volume=254&rft_id=info:doi/10.1016%2Fj.apenergy.2019.113732&rft.externalDocID=S0306261919314199
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0306-2619&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0306-2619&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0306-2619&client=summon