Neural Network-Based Modeling of Electric Vehicle Energy Demand and All Electric Range
A deep neural network-based approach of energy demand modeling of electric vehicles (EV) is proposed in this paper. The model-based prediction of energy demand is based on driving cycle time series used as a model input, which is properly preprocessed and transformed into 1D or 2D static maps to ser...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-04-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/12/7/1396 |
_version_ | 1797999268124950528 |
---|---|
author | Jakov Topić Branimir Škugor Joško Deur |
author_facet | Jakov Topić Branimir Škugor Joško Deur |
author_sort | Jakov Topić |
collection | DOAJ |
description | A deep neural network-based approach of energy demand modeling of electric vehicles (EV) is proposed in this paper. The model-based prediction of energy demand is based on driving cycle time series used as a model input, which is properly preprocessed and transformed into 1D or 2D static maps to serve as a static input to the neural network. Several deep feedforward neural network architectures are considered for this application along with different model input formats. Two energy demand models are derived, where the first one predicts the battery state-of-charge and fuel consumption at destination for an extended range electric vehicle, and the second one predicts the vehicle all-electric range. The models are validated based on a separate test dataset when compared to the one used in neural network training, and they are compared with the traditional response surface approach to illustrate effectiveness of the method proposed. |
first_indexed | 2024-04-11T11:01:56Z |
format | Article |
id | doaj.art-77ac339b5c31448fb8f9ad67453ba579 |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-04-11T11:01:56Z |
publishDate | 2019-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-77ac339b5c31448fb8f9ad67453ba5792022-12-22T04:28:31ZengMDPI AGEnergies1996-10732019-04-01127139610.3390/en12071396en12071396Neural Network-Based Modeling of Electric Vehicle Energy Demand and All Electric RangeJakov Topić0Branimir Škugor1Joško Deur2Faculty of Mechanical Engineering and Naval Architecture, University of Zagreb, 10000 Zagreb, CroatiaFaculty of Mechanical Engineering and Naval Architecture, University of Zagreb, 10000 Zagreb, CroatiaFaculty of Mechanical Engineering and Naval Architecture, University of Zagreb, 10000 Zagreb, CroatiaA deep neural network-based approach of energy demand modeling of electric vehicles (EV) is proposed in this paper. The model-based prediction of energy demand is based on driving cycle time series used as a model input, which is properly preprocessed and transformed into 1D or 2D static maps to serve as a static input to the neural network. Several deep feedforward neural network architectures are considered for this application along with different model input formats. Two energy demand models are derived, where the first one predicts the battery state-of-charge and fuel consumption at destination for an extended range electric vehicle, and the second one predicts the vehicle all-electric range. The models are validated based on a separate test dataset when compared to the one used in neural network training, and they are compared with the traditional response surface approach to illustrate effectiveness of the method proposed.https://www.mdpi.com/1996-1073/12/7/1396electric vehiclesdeep neural networksenergy demand modelingSoC at destinationfuel consumptionall-electric rangebig data |
spellingShingle | Jakov Topić Branimir Škugor Joško Deur Neural Network-Based Modeling of Electric Vehicle Energy Demand and All Electric Range Energies electric vehicles deep neural networks energy demand modeling SoC at destination fuel consumption all-electric range big data |
title | Neural Network-Based Modeling of Electric Vehicle Energy Demand and All Electric Range |
title_full | Neural Network-Based Modeling of Electric Vehicle Energy Demand and All Electric Range |
title_fullStr | Neural Network-Based Modeling of Electric Vehicle Energy Demand and All Electric Range |
title_full_unstemmed | Neural Network-Based Modeling of Electric Vehicle Energy Demand and All Electric Range |
title_short | Neural Network-Based Modeling of Electric Vehicle Energy Demand and All Electric Range |
title_sort | neural network based modeling of electric vehicle energy demand and all electric range |
topic | electric vehicles deep neural networks energy demand modeling SoC at destination fuel consumption all-electric range big data |
url | https://www.mdpi.com/1996-1073/12/7/1396 |
work_keys_str_mv | AT jakovtopic neuralnetworkbasedmodelingofelectricvehicleenergydemandandallelectricrange AT branimirskugor neuralnetworkbasedmodelingofelectricvehicleenergydemandandallelectricrange AT joskodeur neuralnetworkbasedmodelingofelectricvehicleenergydemandandallelectricrange |