Marouane Adnane

Marouane Adnane

Auto-generated profile, based on publicly available information

Marouane Adnane

Department of Electrical Engineering and Computer Engineering, Universit de Sherbrooke, Sherbrooke, QC, Canada

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 February 2021 in IEEE Transactions on Transportation Electrification
Verified
Journal Article
Closed access
MAMarouane Adnane
Marouane Adnane
Bao-Huy NguyenBao-Huy Nguyen
Bao-Huy Nguyen
AKAhmed Khoumsi
Ahmed Khoumsi
JTJoão Pedro F. Trovão
João Pedro F. Trovão
To minimize battery aging of electric vehicles (EVs), it is paramount to manage efficiently their energy consumption. An energy management strategy (EMS) has recently been developed, where batteries and supercapacitors (SCs) are coordinated as a function of the driving mode which is determined manually by the driver. In the present article, we improve the EMS by developing a driving mode predictor (DMP) that determines automatically in real-time the driving mode simply from the speed history of the vehicle. The DMP is designed using supervised learning (SL), a branch of machine learning (ML). A strength of our approach is that it is applicable to predict the driving modes of any EV. To predict the driving modes during a trip made by a given EV, the DMP needs to follow the speed evolution of the EV and know its maximum reachable speed. The integration of the DMP into the EMS results in an enhanced EMS called DMP-based EMS that determines automatically in real-time the power to take from each source of energy of the EV as a function of its speed history. The results obtained from real driving cycles confirm the prediction quality of the DMP and the energy efficiency of the proposed DMP-based EMS.

22 January 2024 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
MAMarouane Adnane
Marouane Adnane
CNChi T. P. Nguyen
Chi T. P. Nguyen
AKAhmed Khoumsi
Ahmed Khoumsi
João Pedro TrovãoJoão Pedro Trovão
João Pedro Trovão
Recently, demand for electric vehicles (EVs) has increased significantly as people are becoming more conscious of the environment and the need to reduce carbon emissions. The introduction of multi-motor systems in EVs has brought new challenges in terms of energy efficiency and performance. This paper presents a Multi-Ensemble Learning (MEL)-based approach to design an Energy Management Strategy (EMS) for a Dual Motor Electric Vehicle (DMEV) where MEL is a new powerful Machine Learning approach implemented using Python programming language. To make our study concrete, we studied a real DMEV that is modeled using Energetic Macroscopic Representation and whose control is simulated using Matlab/Simulin TM . The designed EMS aims to distribute the instant torque between the two electric motors in an efficient manner, with the objective of minimizing energy consumption as much as possible. Contrary to existing EMSs, an important advantage of our designed EMS is that it determines the instant torque distribution in real-time (while the vehicle is running), without knowing in advance how physical parameters (such as the speed and traction force) will evolve during the current trip. The real-time simulation is carried out under unknown driving cycles based on a validated numerical EV model with a significantly lower computational cost while achieving a high degree of accuracy in predicting and allocating torque, and a high degree of performance in terms of energy consumption.

23 June 2023 in Energies
Verified
Journal Article
Open access
PDF file
MAMarouane Adnane
Marouane Adnane
AKAhmed Khoumsi
Ahmed Khoumsi
João Pedro TrovãoJoão Pedro Trovão
João Pedro Trovão
Electric vehicles are growing in popularity as a form of transportation, but are still underused for several reasons, such as their relatively low range and the high costs associated with manufacturing and maintaining batteries. Many studies using several approaches have been conducted on electric vehicles. Among all studied subjects, here we are interested in the use of machine learning to efficiently manage the energy consumption of electric vehicles, in order to develop intelligent electric vehicles that make quick unprogrammed decisions based on observed data allowing minimal electricity consumption. Our interest is motivated by the adequate results obtained using machine learning in many fields and the increasing but still insufficient use of machine learning to efficiently manage the energy consumption of electric vehicles. From this standpoint, we have built this comprehensive survey covering a broad variety of scientific papers in the field published over the last few years. According to the findings, we identified the current trend and revealed future perspectives.

10 April 2025 in IEEE Transactions on Transportation Electrification
Verified
Journal Article
Closed access
MAMarouane Adnane
Marouane Adnane
Bao-Huy NguyenBao-Huy Nguyen
Bao-Huy Nguyen
AKAhmed Khoumsi
Ahmed Khoumsi
João Pedro TrovãoJoão Pedro Trovão
João Pedro Trovão
In the actual context of dual-source electric vehicles (DSEVs), efficient energy management strategies (EMSs) are essential to optimize energy distribution between batteries and supercapacitors (SCs). However, achieving real-time decision-making and adaptability in resource-constrained environments remains a significant challenge. This study addresses these challenges by comparing two advanced machine learning (ML)-based EMSs: driving mode predictor-based EMS (DMP-EMS) and multiensemble learning-based EMS (MEL-EMS). Using signal hardware-in-the-loop (S-HIL) simulation and a Raspberry Pi 4 platform, the two EMSs are evaluated based on various criteria, including performance accuracy, model complexity, training and prediction times, required computing resources, scalability, and energy consumption. The findings highlight the tradeoffs between these EMSs, offering insights into designing tailored EMSs for DSEVs under varying operational demands. While MEL-EMS excels in environments where prediction accuracy is paramount since it offers superior predictive performance suitable for applications demanding high accuracy and scalability, DMP-EMS provides a more efficient and practical solution for real-time energy management in resource-constrained settings.

24 October 2023
Verified
Conference Paper
Closed access
MAMarouane Adnane
Marouane Adnane
CNChi T. P. Nguyen
Chi T. P. Nguyen
AKAhmed Khoumsi
Ahmed Khoumsi
João Pedro TrovãoJoão Pedro Trovão
João Pedro Trovão
The increasing demand for Electric Vehicles (EV s) has made energy efficiency and performance crucial. This paper proposes a Multi-Ensemble Learning-based Energy Management Strategy (EMS) approach for a Dual-Motor Electric Vehicle (DM-EV) to address these challenges. Energetic Macroscopic Representation is used to model the DM-EV, and Matlab/Simulink™ is used to simulate the control. The proposed model is designed with Python programming language and aims to distribute the instant torque between the two electric motors efficiently, minimizing energy consumption in real-time, without prior knowledge of physical parameters. A real-time simulation under an unknown driving cycle was validated using a numerical EV model and achieved promising results while having a significantly lower computational cost compared to existing EMSs. The proposed model shows a high degree of efficiency in predicting and allocating torque, making it a promising solution for efficient energy management in multi-motor EVs.