Skip to main content

Optimizing fast charging protocols for lithium-ion batteries using reinforcement learning: Balancing speed, efficiency, and longevity

Research Abstract
Although lithium-ion batteries are essential for contemporary energy storage applications, maintaining battery longevity, safety, and health frequently clashes with the requirement for quick charging. The problem of developing rapid charging protocols to strike a balance between battery protection and charging speed is addressed in this work. We create an adaptive charging strategy that dynamically modifies charging rates in response to battery conditions while respecting safety limitations including voltage and temperature limits using Reinforcement Learning (RL). In order to maximize performance metrics and avoid degradation, the RL agent is trained in a simulated environment.
To examine their effects on charging time, capacity, temperature, deterioration, energy efficiency, and State of Health (SoH), five charging profiles—constant, decreasing, and alternating current techniques—are assessed. The findings show that quicker charging profiles speed up deterioration, raise temperature, and hasten the drop of SoH even though they shorten charging times. Slower profiles, on the other hand, improve long-term battery health and efficiency by controlling temperature and minimizing deterioration, even though they require longer charging times.
The RL-based approach balances quick charging with battery preservation by implementing a reward system that penalizes dangerous conditions like high voltage or temperature in order to lessen these trade-offs. These results highlight the necessity of sophisticated charging processes to maximize efficiency in battery-dependent systems, such as electric cars and portable devices.
Research Authors
Khairy Sayed, Mahmoud Aref, Mishari Metab Almalki, Mahmoud A Mossa
Research Date
Research Department
Research Journal
Results in Engineering
Research Member
Research Pages
104302
Research Publisher
Elsevier
Research Vol
25
Research Website
https://doi.org/10.1016/j.rineng.2025.104302
Research Year
2025

Feasibility study and economic analysis of PV/wind-powered hydrogen production plant

Research Abstract

In Egypt, the production of power and the associated environmental problems are starting to take the stage. One environmentally responsible way to lessen the power crisis is to employ renewable energy sources effectively and efficiently. This paper proposes to develop a hydrogen energy storage-based green (or environmentally friendly) power plant on many Egyptian cities such as Sohag city. To produce green hydrogen, the proposed power station uses energy storage, solar, and wind power. Energy storage systems are used to store extra energy produced by wind turbines and solar panels and to supply energy when the output of renewable energy is low. An optimized design of the proposed power plant uses hydrogen energy to satisfy peak load requirements and reduce GHG (greenhouse gas) emissions. Electrolysis is the method used in the proposed solar/wind power plant to create hydrogen. Water can be split into hydrogen and oxygen via electrolysis, a process that uses electricity. Renewable energy sources can be used to power this procedure, ensuring that the hydrogen produced is “green” and does not contribute to greenhouse gas emissions. The design of the power plant incorporates advanced electrolysis technology, such as proton exchange membrane (PEM) electrolyzers, which are efficient and well-suited for integrating with renewable energy sources.

Research Authors
Khairy Sayed, Mohamed Khamies, Ahmed G Abokhalil, Mahmoud Aref, Mahmoud A Mossa, Mishari Metab Almalki, Thamer AH Alghamdi
Research Date
Research Department
Research Journal
IEEE Access
Research Member
Research Pages
76304-76318
Research Publisher
IEEE
Research Vol
12
Research Website
https://ieeexplore.ieee.org/abstract/document/10540433
Research Year
2024

A distributed architecture of parallel buck-boost converters and cascaded control of DC microgrids-real time implementation

Research Abstract

To enhance the stability and reliability of the system, the converters’ parallel operation can be cascaded to address the constraints posed by the substantial integration of renewable resources. Buck-boost DC-DC converters are often controlled via a cascaded control approach to allow parallel operation. The converter’s output current and its voltage will be controlled by nested loop control. This study proposes adaptive droop control parameters that are updated and verified online using the principal current sharing loops to minimize the fluctuation in load current sharing. When the converters in the microgrid are paralleled, load sharing will be accomplished using the droop control approach in addition to nested proportional-integral-based voltage and current control loops. To restore the correct voltage across the DC microgrid, an outer addition voltage secondary loop will be used, rectifying any voltage disparities caused by the droop management strategy. Several common load resistances and input voltage variations are used to test the suggested method. Using a linearized model, this work assesses the stability and performance of the proposed method. It then confirms the findings with an adequate model created in MATLAB/SIMULINK, Real-Time Simulation Fundamentals, and hardware-based experiments.

Research Authors
Mohamed A Mesbah, Khairy Sayed, Adel Ahmed, Mahmoud Aref, Mahmoud A Gaafar, Mahmoud A Mossa, Mishari Metab Almalki, Thamer AH Alghamdi
Research Date
Research Department
Research Journal
IEEE Access
Research Member
Research Pages
47483-47493
Research Publisher
IEEE
Research Vol
12
Research Website
https://ieeexplore.ieee.org/abstract/document/10480682
Research Year
2024

Adaptive control approach for accurate current sharing and voltage regulation in DC microgrid applications

Research Abstract

A DC microgrid is an efficient way to combine diverse sources; conventional droop control is unable to achieve both accurate current sharing and required voltage regulation. This paper provides a new adaptive control approach for DC microgrid applications that satisfies both accurate current sharing and appropriate voltage regulation depending on the loading state. As the load increases in parallel, so do the output currents of the distributed generating units, and correct current sharing is necessary under severe load conditions. The suggested control approach raises the equivalent droop gains as the load level increases in parallel and provides accurate current sharing. The droop parameters were checked online and changed using the principal current sharing loops to reduce the variation in load current sharing, and the second loop also transferred the droop lines to eliminate DC microgrid bus voltage fluctuation in the adaptive droop controller, which is different and inventive. The proposed algorithm is tested using a variety of input voltages and load resistances. This work assesses the performance and stability of the suggested method using a linearized model and verifies the results using an acceptable model created in MATLAB/SIMULINK Software Version 9.3 and using Real-Time Simulation Fundamentals and hardware-based experimentation.

Research Authors
Mohamed A Mesbah, Khairy Sayed, Adel Ahmed, Mahmoud Aref, ZMS Elbarbary, Ali Saeed Almuflih, Mahmoud A Mossa
Research Date
Research Journal
Energies
Research Publisher
MDPI
Research Vol
17
Research Website
https://doi.org/10.3390/en17020284
Research Year
2024

The Algorithmic Studio: A PRISMA-Guided Systematic Review for Integrating Artificial Intelligence in Interior Design Education

Research Authors
Myar Mohamed Abdelbasir Sayed, Adham Mokhtar Mostafa Mohammed, and Magdy Mohamed Radwan Hamed
Research Date
Research Journal
9th International Architectural Conference of Assiut University (IACA-9)

The Impact of Mall design patterns on User Congestion: A Space Syntax based Approach

Research Authors
Abrar Mahmoud Abdo, Magdy Mohamed Radwan, and Adham Mokhtar Mostafa Mohammed
Research Date
Research Journal
9th International Architectural Conference of Assiut University (IACA-9)
Subscribe to