Durairaj Chandrakala
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Durairaj Chandrakala has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
V. R. Rajan
Department of Electronics Communication & Engg, T. John Institute of Technology, Bangalore, 560 083, Karnataka, India
2 shared publications- Adhimoolam Sairam
Saveetha University
1 shared publication - Balasubramanian Suganya
Assistant Professor, Department of Computer science and Engineering, School of computing, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, Tamil Nadu, India
1 shared publication - Bichagal Shadaksharappa
Sri Sairam College of Engineering
1 shared publication - Chelliah Srinivasan
Saveetha University
1 shared publication D. Rene Dev
Department of Electronics Communication & Engg, T. John Institute of Technology, Bangalore, 560 083, Karnataka, India
1 shared publication
Latest Publications
- Open Access
- 1 September 2026
- Published by Institute of Advanced Engineering and Science in International Journal of Applied Power Engineering (IJAPE)
- Vol. 15 (3) , 1375-1385
A deep learning approach for electric vehicle battery charging duration estimation using IoT
The rapid development of electric vehicles (EVs) has increased the desire for precise charging duration estimate to enhance charging station administration and elevate customer experience. This research presents a deep learning (DL) architecture that uses internet of things (IoT)-enabled data to categorise charging duration into short, medium, and long classifications. The assessment dataset comprises many numerical and categorical variables affecting battery performance and charging behaviour, providing a thorough foundation for prediction. The system utilises a deep neural network (DNN) architecture with nonlinear transformations and regularisation techniques, trained with adaptive optimisation to provide durable convergence. Extensive experiments indicate that the proposed model achieves an overall accuracy of 99.26%, markedly improving traditional machine learning (ML) techniques. These results highlight the potential of DL to adeptly discern complex linkages in charging dynamics, providing dependable predictions for duration classification. The framework provides an advanced basis for implementation in smart charging infrastructures, facilitating effective scheduling, minimizing waiting times, and endorsing predictive maintenance measures. It enhances the reliability and efficiency of EV charging ecosystems with data-driven, IoT-enabled DL technologies.
- 1 September 2026
- Published by Institute of Advanced Engineering and Science in International Journal of Applied Power Engineering (IJAPE)
- Vol. 15 (3) , 1375-1385
Open AccessA deep learning approach for electric vehicle battery charging duration estimation using IoT
The rapid development of electric vehicles (EVs) has increased the desire for precise charging duration estimate to enhance charging station administration and elevate customer experience. This research presents a deep learning (DL) architecture that uses internet of things (IoT)-enabled data to categorise charging duration into short, medium, and long classifications. The assessment dataset comprises many numerical and categorical variables affecting battery performance and charging behaviour, providing a thorough foundation for prediction. The system utilises a deep neural network (DNN) architecture with nonlinear transformations and regularisation techniques, trained with adaptive optimisation to provide durable convergence. Extensive experiments indicate that the proposed model achieves an overall accuracy of 99.26%, markedly improving traditional machine learning (ML) techniques. These results highlight the potential of DL to adeptly discern complex linkages in charging dynamics, providing dependable predictions for duration classification. The framework provides an advanced basis for implementation in smart charging infrastructures, facilitating effective scheduling, minimizing waiting times, and endorsing predictive maintenance measures. It enhances the reliability and efficiency of EV charging ecosystems with data-driven, IoT-enabled DL technologies.
- Open Access
- 9 June 2026
- Published by Springer Nature in Scientific Reports
A hybrid heuristic-based multi-objective strategy for optimized charging and discharging in plug-in EV energy management
The paper will deal with the problem of optimal charging and discharging coordination of Plug-in Electric Vehicles in a local multi-energy system that will be conducted under uncertain conditions. The current practices are usually based on simplified assumptions and fail to coordinate various energy sources and resources effectively, which restricts their usage in real-life conditions. In order to eliminate these constraints, a hybrid optimization model that involves Rider Optimization and Osprey Optimization integration is suggested. The model developed will take into account both the economic and environmental goals, such as the cost of operation, profitability of the system, and minimization of carbon emission. The lack of certainty in the behavior and generation of the renewable is factored in by using probabilistic modeling, which allows the system to be more realistic. The suggested algorithm constraints global exploration and local exploitation to optimally search the energy scheduling strategies. The outcomes of the simulation display the assumption that the proposed method can deliver the enhanced performance of the operational level as it successfully organizes the activities of distributed energy resources and electric vehicle charging. The model offers computationally effective and flexible framework to be used in practical energy management applications in local multi-energy systems.
- 9 June 2026
- Published by Springer Nature in Scientific Reports
Open AccessA hybrid heuristic-based multi-objective strategy for optimized charging and discharging in plug-in EV energy management
The paper will deal with the problem of optimal charging and discharging coordination of Plug-in Electric Vehicles in a local multi-energy system that will be conducted under uncertain conditions. The current practices are usually based on simplified assumptions and fail to coordinate various energy sources and resources effectively, which restricts their usage in real-life conditions. In order to eliminate these constraints, a hybrid optimization model that involves Rider Optimization and Osprey Optimization integration is suggested. The model developed will take into account both the economic and environmental goals, such as the cost of operation, profitability of the system, and minimization of carbon emission. The lack of certainty in the behavior and generation of the renewable is factored in by using probabilistic modeling, which allows the system to be more realistic. The suggested algorithm constraints global exploration and local exploitation to optimally search the energy scheduling strategies. The outcomes of the simulation display the assumption that the proposed method can deliver the enhanced performance of the operational level as it successfully organizes the activities of distributed energy resources and electric vehicle charging. The model offers computationally effective and flexible framework to be used in practical energy management applications in local multi-energy systems.
- 29 April 2026
- Published by Springer Nature in Journal of Optics
- p. 1-13
Hybrid machine learning for optimized metasurface SPR biosensor in real-time cervical cancer biomarker detection
- 29 April 2026
- Published by Springer Nature in Journal of Optics
- p. 1-13
Hybrid machine learning for optimized metasurface SPR biosensor in real-time cervical cancer biomarker detection
- Open Access
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 3040 (1) , 090009
Industry pollution monitoring using IoT and deep learning technology
Environmental conditions continue to debilitate each year on account of advancement of development and expanding messy discharges from enterprises and cars. Not
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 3040 (1) , 090009
Open AccessIndustry pollution monitoring using IoT and deep learning technology
Environmental conditions continue to debilitate each year on account of advancement of development and expanding messy discharges from enterprises and cars. Not
- Open Access
- 1 December 2023
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 32 (3) , 1327-1336
Performance improvement in photovoltaic-grid system using genetic algorithm
In recent, photov oltaic (PV) power generation has increased in importance. The growing significance of PV power production has generated the demand for enhancing energy efficiency via continuous operation at the maximum power point (MPP). To enable effective MPP trac king, the suggested system integrates a proportional - integral (PI) controller with the p erturb and observe (P&O) technique. In order to improve performance in a PV grid system, this work provides a unique method using a proportional - integral - derivative (PI D) controller optimized using a genetic algorithm (GA). The proposed controller architecture integrates the GA algorithm with a PID controller in the voltage source inverter (VSI) of the PV system. To enable effective grid integration, the GA is used to co ntinually optimize the PID controller settings. The converter’ s design criteria and computations are discussed, and MATLAB simulations are used to assess the system’ s performance. Compared to traditional PID controllers, the observed findings show increas ed efficiency, cheaper cost, and enhanced controllability. The suggested GA - PID controller offers opportunities for more study and development in this area while showing potential for improving PV grid system performance.
- 1 December 2023
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 32 (3) , 1327-1336
Open AccessPerformance improvement in photovoltaic-grid system using genetic algorithm
In recent, photov oltaic (PV) power generation has increased in importance. The growing significance of PV power production has generated the demand for enhancing energy efficiency via continuous operation at the maximum power point (MPP). To enable effective MPP trac king, the suggested system integrates a proportional - integral (PI) controller with the p erturb and observe (P&O) technique. In order to improve performance in a PV grid system, this work provides a unique method using a proportional - integral - derivative (PI D) controller optimized using a genetic algorithm (GA). The proposed controller architecture integrates the GA algorithm with a PID controller in the voltage source inverter (VSI) of the PV system. To enable effective grid integration, the GA is used to co ntinually optimize the PID controller settings. The converter’ s design criteria and computations are discussed, and MATLAB simulations are used to assess the system’ s performance. Compared to traditional PID controllers, the observed findings show increas ed efficiency, cheaper cost, and enhanced controllability. The suggested GA - PID controller offers opportunities for more study and development in this area while showing potential for improving PV grid system performance.