Jeyaraj Senthil Kumar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jeyaraj Senthil Kumar has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Sathiasamuel Charles Raja
Department of Electrical and Electronics Engineering, Thiagarajar College of Engineering, Madurai, India
2 shared publications - Chandrasekaran Kumar
Electronics and Communication Engineering, Rathinam Technical Campus, Coimbatore, Tamil Nadu, India
1 shared publication - Dipti Srinivasan
National University of Singapore
1 shared publication - Felix Joseph Xavier
Electronics and Communication Engineering, Rohini College of Engineering and Technology, Kanyakumari 629401, India
1 shared publication - G. R. Hemanth
Department of Electrical and Electronics Engineering, PSG Institute of Technology and Applied Research, Coimbatore, India
1 shared publication - Hady Habib Fayek
Energy and Renewable Energy Engineering Department, The Egyptian Chinese University, Cairo, Egypt
1 shared publication
Latest Publications
- 11 May 2026
- Published by The Electrochemical Society in Journal of the Electrochemical Society
- Vol. 173 (11)
Sensor Driven Long Short-Term Memory Gate Recurrent Estimation with Deep Reinforcement Learning Based Charge Control for Battery Swapping Station Application
Electric vehicle battery swapping technology can promote the high-quality development of new energy vehicles. Rapid analysis of the state of charge (SOC) is particularly essential for electric vehicle battery swapping. Traditional SOC assessment methods vary in model types and simplification techniques, often leading to skewed SOC estimation and unfair battery-swapping transactions in electric vehicles. To overcome this issue, this paper proposes an integrated method that accurately estimates SOC and controls charging current according to environmental conditions using an LSTM-based Gated Recurrent Estimator combined with a Reinforcement Learning Deep Deterministic Policy Gradient (RLDDPG) controller. The hybrid neural network combining LSTM-GRE and LSTM improves SOC estimation accuracy with minimal sensor data, offers self-optimization, and handles temperature variations without OCV–SOC lookup tables. Additionally, optimizing the charging strategy directly enhances charging efficiency. This study addresses the challenge of fast charging lithium-ion batteries. Using an LSTM-GRE with Deep Reinforcement Learning Deterministic Policy Gradient (LSTM-GRE RLDDPG) charging protocol, it develops an energy-optimization model to find the ideal balance between rapid charging and battery health. The method considers temperature, voltage, SOC, and charging current constraints to achieve efficient charging while minimizing both SOC imbalance and charging time.
- 11 May 2026
- Published by The Electrochemical Society in Journal of the Electrochemical Society
- Vol. 173 (11)
Sensor Driven Long Short-Term Memory Gate Recurrent Estimation with Deep Reinforcement Learning Based Charge Control for Battery Swapping Station Application
Electric vehicle battery swapping technology can promote the high-quality development of new energy vehicles. Rapid analysis of the state of charge (SOC) is particularly essential for electric vehicle battery swapping. Traditional SOC assessment methods vary in model types and simplification techniques, often leading to skewed SOC estimation and unfair battery-swapping transactions in electric vehicles. To overcome this issue, this paper proposes an integrated method that accurately estimates SOC and controls charging current according to environmental conditions using an LSTM-based Gated Recurrent Estimator combined with a Reinforcement Learning Deep Deterministic Policy Gradient (RLDDPG) controller. The hybrid neural network combining LSTM-GRE and LSTM improves SOC estimation accuracy with minimal sensor data, offers self-optimization, and handles temperature variations without OCV–SOC lookup tables. Additionally, optimizing the charging strategy directly enhances charging efficiency. This study addresses the challenge of fast charging lithium-ion batteries. Using an LSTM-GRE with Deep Reinforcement Learning Deterministic Policy Gradient (LSTM-GRE RLDDPG) charging protocol, it develops an energy-optimization model to find the ideal balance between rapid charging and battery health. The method considers temperature, voltage, SOC, and charging current constraints to achieve efficient charging while minimizing both SOC imbalance and charging time.
- 21 October 2024
- Published by Springer Nature in Electrical Engineering
- Vol. 107 (4) , 4873-4896
Integrated PV energy generation system with high-gain converter and CHHO-FLC-based MPPT for grid integration
- 21 October 2024
- Published by Springer Nature in Electrical Engineering
- Vol. 107 (4) , 4873-4896
Integrated PV energy generation system with high-gain converter and CHHO-FLC-based MPPT for grid integration
- Open Access
Reliability Improvement of a Hybrid Electric Vehicle Integrated Distribution System
The recent trend in hybrid electric vehicles (HEV) has increased the need for vehicle charging stations (VCS) in the distribution system. In this condition, the additional load in the system leads to an increase in power loss, reduction in voltage and reliability of the system. The drawbacks of introducing this additional load can be rectified by integrating distributed generation (DG) into the distribution system. In this paper, the ideal location for placing DG is identified through the voltage stability index. The power loss minimization objective function is formulated with all the required constraints to estimate the size of DG required for the distribution system. Moreover, loss of load probability is used as a reliability assessment technique, through which the system reliability is analyzed after assessing the impact of integrating VCS and DG. Simulations are carried out to compare the following cases: a system without VCS and DG, a system that has only VCS and a system that has both VCS and DG. The IEEE 12-bus and 33-bus test systems are considered. In the 12-bus system with both VCS and DG, the power loss is reduced by 56% when compared with the system with only VCS, while the net reliability is also improved. The reliability of the system is evaluated for a 24 h load variation. The proposed work provides an efficient tool to improve the reliability of the system with support from DG.
Open AccessReliability Improvement of a Hybrid Electric Vehicle Integrated Distribution System
The recent trend in hybrid electric vehicles (HEV) has increased the need for vehicle charging stations (VCS) in the distribution system. In this condition, the additional load in the system leads to an increase in power loss, reduction in voltage and reliability of the system. The drawbacks of introducing this additional load can be rectified by integrating distributed generation (DG) into the distribution system. In this paper, the ideal location for placing DG is identified through the voltage stability index. The power loss minimization objective function is formulated with all the required constraints to estimate the size of DG required for the distribution system. Moreover, loss of load probability is used as a reliability assessment technique, through which the system reliability is analyzed after assessing the impact of integrating VCS and DG. Simulations are carried out to compare the following cases: a system without VCS and DG, a system that has only VCS and a system that has both VCS and DG. The IEEE 12-bus and 33-bus test systems are considered. In the 12-bus system with both VCS and DG, the power loss is reduced by 56% when compared with the system with only VCS, while the net reliability is also improved. The reliability of the system is evaluated for a 24 h load variation. The proposed work provides an efficient tool to improve the reliability of the system with support from DG.
- 15 April 2020
- Published by Taylor & Francis in Advances in Building Energy Research
- Vol. 16 (2) , 145-170
Cost effective energy consumption in a residential building by implementing demand side management in the presence of different classes of power loads
In the present scenario, in order to meet the growing electricity demand, demand side management (DSM) is one among the various approaches used in smart grid. By applying DSM at the customer side, various benefits such as reduction in electricity cost, reduction in peak demand, and improvement in load factor can be achieved. This paper proposes a new architecture, namely, Intelligent Universal Load Management System (IULMS) to implement DSM based on load shifting approach for a residential building in the presence of different classes of loads. In this work, the objective is to minimize the cost of electricity consumption and there are several constraints imposed by the device types operating in the system and it is solved by Binary Grey Wolf Optimization algorithm. The objective function is non-linear in nature because the price of electricity varies each hour. A real-time system involving residential building users of Agrini Apartment in Madurai, Tamilnadu, India is discussed. Further, the potential of DSM is analyzed. The minimization of electricity consumption cost, peak demand, and Peak to Average Ratio (PAR) are validated for each test case.
- 15 April 2020
- Published by Taylor & Francis in Advances in Building Energy Research
- Vol. 16 (2) , 145-170
Cost effective energy consumption in a residential building by implementing demand side management in the presence of different classes of power loads
In the present scenario, in order to meet the growing electricity demand, demand side management (DSM) is one among the various approaches used in smart grid. By applying DSM at the customer side, various benefits such as reduction in electricity cost, reduction in peak demand, and improvement in load factor can be achieved. This paper proposes a new architecture, namely, Intelligent Universal Load Management System (IULMS) to implement DSM based on load shifting approach for a residential building in the presence of different classes of loads. In this work, the objective is to minimize the cost of electricity consumption and there are several constraints imposed by the device types operating in the system and it is solved by Binary Grey Wolf Optimization algorithm. The objective function is non-linear in nature because the price of electricity varies each hour. A real-time system involving residential building users of Agrini Apartment in Madurai, Tamilnadu, India is discussed. Further, the potential of DSM is analyzed. The minimization of electricity consumption cost, peak demand, and Peak to Average Ratio (PAR) are validated for each test case.
- 5 October 2017
- Published by Wiley in International Journal of Energy Research
- Vol. 42 (3) , 1066-1087
Hybrid renewable energy-based distribution system for seasonal load variations
- 5 October 2017
- Published by Wiley in International Journal of Energy Research
- Vol. 42 (3) , 1066-1087
Hybrid renewable energy-based distribution system for seasonal load variations