Post Date
Jun 19 2023

LUMS Energy Institute - Housing Brilliant Minds

Huzaifa Rauf, a brilliant PhD scholar from the Department of Electrical Engineering, has within a year earned two significant accolades - the prestigious “Center for Advanced Life Cycle Engineering (CALCE) at the University of Maryland Awards” for his outstanding performance and lasting contribution on “Safe Energy Storage Research”, and the publication of his research paper in the renowned Elsevier’s “Journal for Energy Storage”.  

The rise and widespread adoption of electric vehicles (EVs) in recent decades has been primarily fueled by advancements in battery and power technologies and the urgent need to curb greenhouse gas emissions. However, unlike traditional fuel-driven vehicles, EVs face a significant challenge—the degradation of their batteries—which limits their overall lifespan. This issue is particularly concerning considering the resource-intensive nature of battery production, as short-lived batteries have an unintended adverse effect on the environment. Recognising this critical problem, Huzaifa is actively involved in a research group at SSE, LUMS Energy Institute, dedicated to enhancing the area of renewable energy analytics, smart grids, and energy efficiency. 

During Huzaifa’s time as a visiting scholar at the University of Maryland, he worked under the supervision of Prof Michael Pecht (member SBASSE advisory board) and Dr Michael David Osterman at CALCE. His dedication and expertise in applying AI and machine learning for reliability improvement in electric vehicle batteries were instrumental in earning him the CALCE award, making him the first visiting PhD from any country to receive this prestigious honour from the Centre. As part of the award, Huzaifa also received a funding grant of $5,000, acknowledging his exceptional research accomplishments. 

“Having worked at the initial phase of the battery degradation, swelling and thermal runaway project, I am confident that this stream is going to make a significant impact in domain of energy storage.” Huzaifa expressed great enthusiasm for having his work recognised. 

During the advisory board meeting, Dr Naveed and researchers from the LUMS Energy Institute showcased their innovative replaceable electric vehicle batteries to the board members, including Prof Michael Pecht. 


In addition to the research award, Huzaifa has also published a paper titled "A Novel Smart Feature Selection Strategy of Lithium-ion Battery Degradation Modelling for Electric Vehicles Based on Modern Machine Learning Algorithms", under the supervision of Dr Naveed Arshad, founder LUMS Energy Institute. 

The paper highlights the importance of accurately predicting battery capacity loss to ensure the batteries' longevity, safety, and reliable operation. To achieve this, the researchers propose a smart feature selection (SFS) strategy-based machine learning framework. The SFS method selects relevant input parameters from battery data from the current and previous time steps, which are then utilized for model training and testing. 


Architecture of the framework for battery capacity loss prediction. 

The results demonstrate that the proposed SFS method, in combination with various machine learning algorithms, significantly enhances the prediction accuracy and reduces the mean absolute error for battery capacity loss. The paper also emphasizes the importance of predicting a battery calendar, the degradation of a battery’s life over time whether or not it’s used, and cyclic loss, the gradual decrease in battery capacity caused by repeated charge and discharge cycles.  Furthermore, it showcases the improved performance achieved by combining the SFS method with machine learning algorithms such as Gaussian Process Regression (GPR), random forest (RF), and XGBoost. This research presents a novel approach to feature selection-based machine learning for independently predicting battery calendar and cyclic loss, making it a valuable contribution to the field.

The publication highlights Huzaifa’s innovative approach to selecting smart features in modelling lithium-ion battery degradation, which has significant implications for electric vehicle performance and longevity. The research paper stands as a testament to his commitment to advancing the field of safe energy storage.