Day-ahead forecast of electric vehicle charging demand with a recurrent neural network

Gilles Van Kriekinge; Cedric De Cauwer; Nikolaos Sapountzoglou; Thierry Coosemans; Maarten Messagie

Day-ahead forecast of electric vehicle charging demand with a recurrent neural network

Gilles Van Kriekinge, Cedric De Cauwer, Nikolaos Sapountzoglou, Thierry Coosemans, Maarten Messagie

Onderzoeksoutput: Unpublished paper

8 Downloads (Pure)

Samenvatting

The increasing penetration rate of electric vehicles, associated with a growing charging demand, could induce a negative impact on the electric grid, such as higher peak power demand. To support the electric grid, and to anticipate these peaks, a growing interest exists to forecast the day-ahead charging demand of electric vehicles. This paper proposes the use of a state-of-the-art deep neural network to forecast the day-ahead charging demand of electric vehicles with a time resolution of 15 minutes. The forecaster is applied on an important use case of a hospital in Brussels, with recent charging sessions records.

Originele taal-2	English
Aantal pagina's	9
Status	Published - 13 apr 2021
Evenement	The 34th International Electric Vehicle Symposium & Exhibition - Nanjing, China Duur: 25 jun 2021 → 28 jun 2021 http://www.evs34.org.cn/

Conference

Conference	The 34th International Electric Vehicle Symposium & Exhibition
Verkorte titel	EVS34
Land/Regio	China
Stad	Nanjing
Periode	25/06/21 → 28/06/21
Internet adres	http://www.evs34.org.cn/

Toegang tot document

paper_finalFinal published version, 529 KB

Citeer dit

@conference{a40627cc8e654b699dc5e6b453307d24,

title = "Day-ahead forecast of electric vehicle charging demand with a recurrent neural network",

abstract = "The increasing penetration rate of electric vehicles, associated with a growing charging demand, could induce a negative impact on the electric grid, such as higher peak power demand. To support the electric grid, and to anticipate these peaks, a growing interest exists to forecast the day-ahead charging demand of electric vehicles. This paper proposes the use of a state-of-the-art deep neural network to forecast the day-ahead charging demand of electric vehicles with a time resolution of 15 minutes. The forecaster is applied on an important use case of a hospital in Brussels, with recent charging sessions records.",

author = "{Van Kriekinge}, Gilles and {De Cauwer}, Cedric and Nikolaos Sapountzoglou and Thierry Coosemans and Maarten Messagie",

year = "2021",

month = apr,

day = "13",

language = "English",

note = "The 34th International Electric Vehicle Symposium & Exhibition, EVS34 ; Conference date: 25-06-2021 Through 28-06-2021",

url = "http://www.evs34.org.cn/",

}

TY - CONF

T1 - Day-ahead forecast of electric vehicle charging demand with a recurrent neural network

AU - Van Kriekinge, Gilles

AU - De Cauwer, Cedric

AU - Sapountzoglou, Nikolaos

AU - Coosemans, Thierry

AU - Messagie, Maarten

PY - 2021/4/13

Y1 - 2021/4/13

N2 - The increasing penetration rate of electric vehicles, associated with a growing charging demand, could induce a negative impact on the electric grid, such as higher peak power demand. To support the electric grid, and to anticipate these peaks, a growing interest exists to forecast the day-ahead charging demand of electric vehicles. This paper proposes the use of a state-of-the-art deep neural network to forecast the day-ahead charging demand of electric vehicles with a time resolution of 15 minutes. The forecaster is applied on an important use case of a hospital in Brussels, with recent charging sessions records.

AB - The increasing penetration rate of electric vehicles, associated with a growing charging demand, could induce a negative impact on the electric grid, such as higher peak power demand. To support the electric grid, and to anticipate these peaks, a growing interest exists to forecast the day-ahead charging demand of electric vehicles. This paper proposes the use of a state-of-the-art deep neural network to forecast the day-ahead charging demand of electric vehicles with a time resolution of 15 minutes. The forecaster is applied on an important use case of a hospital in Brussels, with recent charging sessions records.

M3 - Unpublished paper

T2 - The 34th International Electric Vehicle Symposium & Exhibition

Y2 - 25 June 2021 through 28 June 2021

ER -

Day-ahead forecast of electric vehicle charging demand with a recurrent neural network

Samenvatting

Conference

Toegang tot document

Vingerafdruk

Citeer dit