TY - JOUR
T1 - Data-Driven EV Charging Load Forecasting and Smart Charging
AU - Dai, Xuewu
AU - Li, Handong
AU - Olanrewaju, Israel
AU - Kotter, Richard
AU - Putrus, Ghanim
AU - Aslam, Nauman
AU - Bentley, Edward
AU - Wang, Yue
AU - Marzband, Mousa
AU - Das, Ridoy
AU - Van der Hoogt, Jorden
AU - Portvik, Sture
PY - 2023
Y1 - 2023
N2 - Electrical Vehicles (EVs) have been proposed as a solution for decarbonizing road transport. Smart charging is ebential to coordinate EV energy demand with the requisite peak power supply. The performance of smart charging highly depends on understanding the EVs' charging behaviour (charging patterns and energy demands), and an accurate forecasting of the EV energy demands are ebential for designing a smart charging scheme. This paper presents findings from analysing 3 years' data of an Oslo Vulkan parking garage pilot, one of the largest hybrid public/commercial/residential parking garages for EV charging in Norway/Europe. A long-short-term-memory (LSTM) regression network is developed to predict hourly EV charging demand with a Weighted Absolute Percentage Error of 30.5%. The analysis suggests that a smart charging strategy is needed to shave the peak demand during 19:00-21:00.
AB - Electrical Vehicles (EVs) have been proposed as a solution for decarbonizing road transport. Smart charging is ebential to coordinate EV energy demand with the requisite peak power supply. The performance of smart charging highly depends on understanding the EVs' charging behaviour (charging patterns and energy demands), and an accurate forecasting of the EV energy demands are ebential for designing a smart charging scheme. This paper presents findings from analysing 3 years' data of an Oslo Vulkan parking garage pilot, one of the largest hybrid public/commercial/residential parking garages for EV charging in Norway/Europe. A long-short-term-memory (LSTM) regression network is developed to predict hourly EV charging demand with a Weighted Absolute Percentage Error of 30.5%. The analysis suggests that a smart charging strategy is needed to shave the peak demand during 19:00-21:00.
KW - Charging Demand Forecasting
KW - Data-Driven Analysis
KW - Electric Vehicles
KW - Smart Charging
UR - http://www.scopus.com/inward/record.url?scp=85182939468&partnerID=8YFLogxK
U2 - 10.1016/j.trpro.2023.11.827
DO - 10.1016/j.trpro.2023.11.827
M3 - Conference article
AN - SCOPUS:85182939468
SN - 2352-1457
VL - 72
SP - 2832
EP - 2839
JO - Transportation Research Procedia
JF - Transportation Research Procedia
T2 - 2022 Conference Proceedings Transport Research Arena, TRA Lisbon 2022
Y2 - 14 November 2022 through 17 November 2022
ER -
