Energy Engineering and Power Technology, Computer Engineering, Electrical and Electronic Engineering, Renewable Energy, Sustainability and the Environment
11
Scopus Publications
2583
Scholar Citations
21
Scholar h-index
49
Scholar i10-index
Scopus Publications
HYBRID FEDERATED NEURAL–OBSERVER PREDICTIVE CONTROL FOR ROBUST ELECTRIC VEHICLE BATTERY MANAGEMENT V Rajesh Kumar, K Mahesh, R Dhanush Journal of Engineering and Technology for Industrial Applications, 2026 The rapid growth of electric vehicles (EVs) has intensified the demand for reliable battery management systems (BMS) capable of ensuring safety, longevity, and performance under diverse operating conditions. Conventional observers such as the Extended Kalman Filter (EKF) and data-driven neural networks have shown limitations in scalability, robustness to noise, and interpretability. This paper proposes a Hybrid Federated Neural–Observer Predictive Control (HFNOPC) framework for robust EV battery management. The framework integrates three innovations: (i) a robust super-twisting sliding observer for noise-resilient state estimation of state-of-charge (SOC), state-of-health (SOH), and temperature; (ii) a physics-guided neural residual network that enhances the baseline equivalent circuit and thermal models by capturing nonlinearities due to aging and hysteresis; and (iii) a federated learning strategy that enables distributed EVs to collaboratively train the neural residual component without sharing raw data, thus ensuring scalability and privacy. The enhanced state estimates are coupled with a model predictive control (MPC) scheme, which optimizes charge–discharge trajectories subject to safety and thermal constraints. Simulation studies demonstrate that the proposed HFNOPC reduces SOC estimation error by up to 32% compared with EKF and decreases control cost by 24% compared with conventional PID–based charging strategies. Furthermore, robustness tests under ±10% sensor noise and thermal stress confirm improved stability and accuracy. These results highlight the potential of the proposed framework as a next-generation BMS solution, offering interpretability, robustness, and fleet-wide scalability, thus paving the way for safer and more efficient EV deployment.
Explainable Machine Learning Approach for Transmission Line Fault Identification Using Random Forest, XGBoost, and CatBoost Ijjada Ramesh, Mahesh K., V. Rajesh Kumar, Kanaka Raju Kalla Proceeding of International Conference on Computing Communication Control and Cyber Physical Systems I5cps 2026, 2026 Precise detection of faults in transmission lines is key to the reliability and security of the modern power systems. This paper gives a comparative analysis of three ensemble machine learning models Random Forest, CatBoost and XGBoost on the classification of healthy conditions and line-to-ground (LG) faults. The data is 16,004 labeled samples of one normal state and three LG fault scenarios. Following the standardized preprocessing and systematic hyperparameter, the models were tested in terms of accuracy, precision, recall, and F1-score. Random Forest and XGBoost obtained the best accuracy of 99.9584%, and CatBoost performed a little worse at 99.9167%. Confusion matrix analysis proves that there are few misclassifications and appear only in marginal temporary instances. To ensure interpretability, Partial Dependence Plots (PDP) and Individual Conditional Expectation (ICE) analyses were used. The results prove that Random Forest provide very fast and well explainable solutions thst can be used in real time intelligent grid monitoring applications and protection.
Fault Classification and Detection in Transmission Lines by Hybrid Algorithm Associated Support Vector Machine V. Rajesh Kumar, P. Aruna Jeyanthy Transactions on Emerging Telecommunications Technologies, 2025 This work proposes a unique machine‐learning method based on optimization for the categorization and identification of defects in transmission lines. The novel hybrid optimization algorithm termed as the Chimpanzee inherited Squirrel search strategy (CI‐SSS) optimization technique is used in the proposed approach. The proposed CI‐SSS algorithm inherits the concept of chimps and squirrels in attaining their food with remarkable intelligence. The proposed approach involves optimizing the SVM's parameters to improve the proposed model's accuracy in identifying and classifying transmission line faults. The accuracy and error metrics of the suggested method is studied. The accuracy CI‐SSS is 98.82%, which is 11.35%, 5.41%, 0.84%, and 9.55% higher than methods, like GWO, DA, SSA, and CH, correspondingly. Similarly, the measure of MAE using the proposed CI‐SSS‐based SVM model is 0.0104, which is 84.5%, 87.7%, 85.73%, and 62.85% finer than the traditional methods, namely GWO, DA, SSA, and CH, respectively. Hence, the suggested strategy offers improved performance in classifying and detecting transmission line faults.
Modernizing War Tanker for Defence Using LoRa Communication and GPS Tracking Gagandeep B M, V. Rajesh Kumar, Mahesh K., Bharath G Proceedings of 2025 International Conference on Signal Processing Computation Electronics Power and Telecommunication Iconscept 2025, 2025 Modern defense missions rely heavily on the secure and continuous tracking of mobile logistic assets such as war tankers. In contested environments where communication infrastructure may be compromised, this work introduces a LoRa-based monitoring system integrated with GPS tracking and enhanced security features. The proposed design incorporates frequency-hopping spread spectrum (FHSS)-based anti-jamming, AES-128 encryption for secure telemetry, and an adaptive satellite fallback mechanism to ensure mission continuity during GNSS-denied conditions. A communication link budget is formulated using the COST-231 Hata model at 868 MHz, and simulation results confirm a reliable range of 10.2 km in semi-urban terrain with received power above −132 dBm. Kalman-filtered GPS reduces localization error by 65.4% compared to raw NMEA data. Hardware validation using ESP32-SX1276 demonstrates latency below 410 ms and a 42% improvement in battery endurance due to optimized transmission duty cycling. The system offers a resilient, scalable, and energy-efficient solution for defense logistics monitoring.
A Comparative Study of Computational Intelligence Algorithms for Fault Detection in Smart Grids V. Rajesh Kumar, Trinadha Burle, Parvathi, Weza Dgersiniski Mario De Sousa, S. Vinson Joshua, Bachina Harish Babu 13th IEEE International Conference on Smart Grid Icsmartgrid 2025, 2025 This paper extensively analyzes five leading computational intelligence (CI) algorithms--Artificial Neural Network (ANN), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest (RF) and Extreme Gradient Boosting (XGBoost)--for fault detection in smart grids. Each model is thoroughly reviewed with respect to classification accuracy, precision, recall, F1-score, AUC, computational power and storage space requirements to determine which algorithm may best suit your needs based on performance figures. XGBoost outperformed all other methods for nearly every evaluation criterion. In addition to achieving 97.22 % accuracy and 98.33 % AUC overall it also provided the most accurate classifications for every type of fault too. With inference time of only <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$0.14 \text{ms} /$</tex> sample, XGBoost also offered the fastest performance and showed strong robustness under noisy or incomplete samples. Close behind, Random Forest achieved competitive results in relation to its smaller computational costs. In contrast, KNN was fastest to train But it had a slower inference and worse robustness than Random Forest, making it unsuitable for work real-time environments. The results suggest that XGBoost is the most suitable algorithm for detecting faults in smart grids: it provides a good balance of accuracy, speed and robustness. These insights establish a solid foundation for future research on hybrid as well as edge-deployable CI models in smart grid applications.
Fault Classification and Location in Transmission Lines using Attention Driven Dual-Stage Deep Architecture Network (ADDA-Net) V.Rajesh Kumar, Jenipa. R, S.Ravindran, P.Vetrivel, S.Udaiyakumar, Mahesh K Proceedings of 2025 International Conference on Signal Processing Computation Electronics Power and Telecommunication Iconscept 2025, 2025 Reliable fault detection, classification, and location are critical for ensuring the stability and resilience of modern power transmission networks. Conventional signal processing and machine learning approaches face challenges in handling noisy measurements, high-dimensional data, and fault conditions with overlapping features. In response to these challenges, this work introduces an Attention-Driven Dual-Stage Deep Architecture Network (ADDA-Net) designed for transmission line fault classification and location estimation. The architecture employs convolutional layers to extract discriminative features, while two attention modules are incorporated to emphasize both temporal variations and spatial dependencies within the signals. Finally, fully connected layers are utilized to perform fault type classification and to estimate the corresponding fault location. A dataset comprising simulated fault scenarios, including single-line-to-ground, double-line-to-ground, double-line, and three-phase faults, was used for evaluation. Results demonstrate that ADDA-Net achieves superior accuracy in both classification (99.2%) and location estimation (mean error <0.5 km), outperforming CNN, SVM, and traditional classifiers. The proposed framework provides a robust and scalable solution for intelligent protection of transmission networks.
Optimization-Assisted CNN Model for Fault Classification and Site Location in Transmission Lines V. Rajesh Kumar, P. Aruna Jeyanthy, R. Kesavamoorthy International Journal of Image and Graphics, 2024 The theme of the paper is to emphasize the detection and classification of faults and their site location in the transmission line using machine learning techniques which help to indemnify the foul-up of the humans in identifying the site and type of occurrence of fault. Moreover, the transient stability is a supreme one in power systems and so the disturbances like faults are required to be separated to preserve the transient stability. In general, the protection of the transmission line includes the installation of relays at both ends of the line that constantly monitor voltages and currents and operate unless a fault occurs on a line. Therefore, this paper intends to introduce a novel transmission line protection model by exploiting the hybrid optimization concept to train the Convolutional Neural Network (CNN). Here, the fault detection, classification and site location are diagnosed by using CNN which is trained and tested by making use of diverse synthetic field data derived from the simulation models of distinct types of transmission lines. Hence, the location and the type of faults will be predicted by the CNN depending on the fault signal characteristics which are optimally trained by a new hybrid algorithm named Chicken Swarm Insisted Spotted Hyena (CSI-SH) Algorithm that hybrids both the concept of Spotted Hyena Optimization (SHO) and Chicken Swarm Optimization (CSO). Finally, the proposed method based on CNN for fault classification and site location of transmission lines is implemented in MATLAB/Simulink and the performances are compared with various measures like classification accuracy, fault detection rate and so on.
Lyrebird-Optimized PI Regulator for Enhanced Load Frequency Control in Two-Area Systems P Akila., P. Kezia Joy Kumari, B.M Swetha., E Kavitha., K Mahesh, V. Rajesh Kumar 2024 IEEE International Conference on Information Technology Electronics and Intelligent Communication Systems Iciteics 2024, 2024 This paper introduces a groundbreaking approach to Load Frequency Control (LFC) in two-area interconnected power systems through the development of a Lyrebird-Optimized Proportional-Integral (PI) controller. The crux of this research lies in the innovative application of a novel optimization algorithm inspired by the lyrebird's exceptional mimicry capabilities, aimed at auto-tuning the PI controller parameters for improved system response to load variations. Traditional PI controllers, while prevalent for their simplicity, often fall short in dynamic environments due to the criticality of parameter tuning. The proposed Lyrebird-Optimized Algorithm (LOA) addresses this limitation by iteratively adjusting the PI parameters to find an optimal balance, significantly enhancing the system's stability and response characteristics. The proposed controller demonstrate superior performance in minimizing frequency deviations, reducing settling times, and maintaining system stability under varying load conditions. This study not only paves the way for more efficient and resilient power system operations but also opens new avenues for applying bio-inspired algorithms in complex engineering optimization problems.
Fault Classification & Detection in IEEE 34 Bus System Using Convolutional Neural Network V.Rajesh Kumar, P.Aruna Jeyanthy, K Mahesh, P Akila, V S Thrisha, B M Swetha 2024 15th International Conference on Computing Communication and Networking Technologies Icccnt 2024, 2024 This paper presents a novel approach by means of Convolutional Neural Networks (CNNs) for fault classification and detection in the IEEE 34 bus system, which serves as a representative model for distribution networks. The IEEE 34 bus system is known for its complexity, featuring multiple buses, branches, and loads, making it an ideal testbed for evaluating advanced fault management techniques. The proposed CNN-based methodology leverages the ability of CNNs to automatically learn hierarchical features from system data, such as voltage and current measurements, without the need for manual feature extraction. The key contributions of this paper include the development and implementation of a CNN architecture tailored for fault classification and detection tasks in the IEEE 34 bus system. The CNN model is trained using labeled data sets containing information about different fault scenarios, including 1-phase, 2-phase, and 3-phase faults. The training process involves optimizing the network parameters to improve accuracy and robustness in fault identification. Simulation results demonstrate the effectiveness of the CNN-based approach in accurately classifying and detecting faults in the IEEE 34 bus system. The CNN model shows high accuracy rates in distinguishing between different fault types and provides rapid response times for fault detection, thereby enhancing the overall reliability and resilience of the distribution network. The implications of this research extend to the broader context of intelligent fault management systems in power engineering. By harnessing the capabilities of CNNs, power system operators can benefit from more efficient and automated fault management processes, leading to improved system performance, reduced downtime, and enhanced grid reliability.
Phytochemical Profiling and Antifungal Activity of Mullein ( Verbascum thapsus ) Tissue Oils R Singh, A Kumar, M Gangwal, S Kalra, V Bari, R Wusirika, V Kumar Chemistry & Biodiversity 23 (5), e71342 , 2026 2026
Mechanical and Thermal Characterization of Natural Composites for Sustainable Applications V Kumar, AK Verma, PB Deshmukh Journal of Research and Applications in Mechanical Engineering 14 (2) , 2026 2026
Molecular Pathways and Therapeutic Frontiers in Cancer Cachexia: Integrating Inflammatory and Non-Inflammatory Mechanisms D Anjan, SN Rasool, V Kumar Clinical Nutrition ESPEN, 103295 , 2026 2026
Grouped stakeholders' journeys: a dynamic social impact theory perspective MK Clark, LD Hollebeek, V Kumar, I Riivits‐Arkonsuo, Y Liu Psychology & Marketing , 2026 2026
An Interpretable Machine Learning Approach to Real-Time Anomaly Detection in High-Speed Network Traffic DK Bhattacharyya, JK Kalita, L Breiman, V Chandola, A Banerjee, ... 2026
Synergistic effects of elevated CO2 and high temperature on productivity, plant and soil nitrogen in chickpea (Cicer arietinum) varieties B Chakrabarti, S Kannojiya, A Bhatia, A Sharma, V Kumar, RC Harit The Indian Journal of Agricultural Sciences 96 (4) , 2026 2026
Measurement and determinants of economic inequality between migrants and non-migrants: evidence from Oaxaca-Blinder decomposition analysis of Uttar Pradesh, India V Kumar, KC Pradhan Journal of the Asia Pacific Economy 31 (2), 532-562 , 2026 2026 Citations: 1
Unveiling the Healing Potential of Marsilea minuta Linn. (Sunishannaka): An Integrative Overview of Phytochemistry, Therapeutic Value, and Toxicological Aspects S Singh, V Charde, V Kumar, M Saddam, G Dane, SK Lale Chemistry & Biodiversity 23 (4), e03754 , 2026 2026
Advancing crop-climate resilience through plant biotechnology for sustainable agriculture VR Kumar, S Dash, RM Kenchappa, K Awasthi, T Singh, L Dhingra, ... Agricultural Biotechnology Journal 18 (1), 363-380 , 2026 2026
Customer Acquisition Through Intermediaries (vs. Brand) Shapes Lifetime Value: Evidence From the Hotel Industry A Leszkiewicz, S Sunder, V Kumar, CS Dev Production and operations management, 10591478261437885 , 2026 2026
Combustion based orthorhombic Y3GaO6: Dy3+ phosphor: Structural stability, morphology and luminescence studies for optoelectronic applications R Jangra, D Singh, R Kajal, B Dahiya, E Poonia, P Kumar, V Kumar, ... Inorganic Chemistry Communications, 116405 , 2026 2026 Citations: 2
SACRED JOURNEYS IN A TURBULENT ERA: RELIGIOUS TOURISM'S TRANSFORMATION AND THE QUEST FOR AUTHENTICITY (2001-2025) K PHANPANYA, N CHANCHAIPITIPHAT, S BOONMUN, V KUMAR Procedia of Multidisciplinary Research 4 (2), 27-27 , 2026 2026
Decoding Solute–Co-solute Interactions: A Combined Investigation of Bulk and Sonic Behaviour of L-Serine and L-Leucine in Potassium Oxalate (KOX) Solutions S Sharma, R Sharma, V Kumar, S Singh, N Nkosi, MM Tshibangu, ... Journal of Solution Chemistry, 1-29 , 2026 2026 Citations: 1
USING THE TRIGLYCERIDE-GLUCOSE INDEX TO MEASURE INSULIN RESISTANCE AND PREDICT DIABETIC NEPHROPATHY. S Karamullah, S Arshad, T Hussain, V Kumar, U Mirza, M Ashraf International Journal of Medicine & Public Health 16 (1), 2056 , 2026 2026
Effect of Zinc application on growth and nutritional composition of sorghum fodder varieties S Verma, M Kour, V Kumar, S Kour, B Singh Range Management and Agroforestry 47 (1), 1-7 , 2026 2026
Ameliorative effect of roxithromycin against prostate inflammation-induced chronic pelvic pain in a preclinical model. P Das, S Vangaveti, V Kumar Canadian Journal of Physiology and Pharmacology 104, 1-9 , 2026 2026
Stepped Nanopillar Array-Based Ultra-wideband, Wide Angle, and Polarization Insensitive Plasmonic Nano-absorber For Solar Energy Harvesting V Kumar, S Kumar, S Kumar Plasmonics 21 (1), 1127-1138 , 2026 2026 Citations: 3
Herbicidal Efficacy of Imazethapyr for Weed Management in Chickpea (Cicer arietinum L.) under Lateritic Soils of West Bengal M Kumar, P Ghosh, V Kumar, R Kumar Journal of Advances in Biology & Biotechnology 28 (2), 1646-1655 , 2025 2025
RELIGION IN HUMAN SOCIETY: HOW HAS ITS MEANING, ROLE, AND ADAPTATION EVOLVED ACROSS ERAS? W JOEMSITTIPRASERT, P BUNMON, T VIPAPORN, V KUMAR Thai Man and Society Review 1 (1), 4-4 , 2025 2025
Ethanol Blending and CO 2 Mitigation in India: An ARDL Approach with Monetized Climate Benefits V Kumar, AR Sinha, M Kumar 2025 International Conference on Decision Aid Sciences and Applications … , 2025 2025
MOST CITED SCHOLAR PUBLICATIONS
Titanium tetrachloride, an efficient and convenient reagent for thioacetalization1, 1 V Kumar, S Dev Tetrahedron Letters 24 (12), 1289-1292 , 1983 1983 Citations: 154
Analysing urban solid waste in developing countries: a perspective on Bangalore, India P Van Beukering, M Sehker, R Gerlagh, V Kumar Collaborative Research in the Economics of Environment and Development , 1999 1999 Citations: 118
Online cage rotor fault detection using air-gap torque spectra VV Thomas, K Vasudevan, VJ Kumar IEEE transactions on energy conversion 18 (2), 265-270 , 2003 2003 Citations: 92
Analysing urban solid waste in developing countries: a perspective on Bangalore PV Beukering, M Sehker, R Gerlagh, V Kumar Collaborative Research in the Economics of Environment and Development … , 1999 1999 Citations: 81
Chemistry of ayurvedic crude drugs—VII guggulu (resin from Commiphora mukul)—6: absolute stereochemistry of guggultetrols V Kumar, S Dev Tetrahedron 43 (24), 5933-5948 , 1987 1987 Citations: 73
Problems of solid waste management in Indian cities V Kumar, RK Pandit International Journal of Scientific and Research Publications 3 (3), 1-9 , 2013 2013 Citations: 69
Behaviour of RCC beams after exposure to elevated temperatures A Kumar, V Kumar Journal of the Institution of Engineers. India. Civil Engineering Division … , 2003 2003 Citations: 69
Modulated iontophoretic delivery of small and large molecules through microchannels V Kumar, AK Banga International Journal of Pharmaceutics 434 (1-2), 106-114 , 2012 2012 Citations: 60
Intradermal and follicular delivery of adapalene liposomes V Kumar, AK Banga Drug development and industrial pharmacy 42 (6), 871-879 , 2016 2016 Citations: 54
Organised food retailing: a blessing or a curse? V Kumar, Y Patwari, HN Ayush Economic and Political Weekly, 67-75 , 2008 2008 Citations: 50
Infant and young child feeding behaviors among working mothers in India: Implications for global health policy and practice V Kumar, G Arora, IK Midha, YP Gupta International Journal of MCH and AIDS 3 (1), 7 , 2015 2015 Citations: 34
Fibrinocoagulopathy in maturity onset diabetes mellitus and atherosclerosis RN Banerjee, AL Sahni, V Kumar Thrombosis and Haemostasis 30 (04), 123-132 , 1973 1973 Citations: 33
Cation self-diffusion in single crystal CaO V Kumar, YP Gupta Journal of Physics and Chemistry of Solids 30 (3), 677-685 , 1969 1969 Citations: 30
Influence of corrosion inhibitors in reinforced concrete–A state of art of review S Yuvaraj, K Nirmalkumar, VR Kumar, R Gayathri, K Mukilan, ... Materials Today: Proceedings 68, 2406-2412 , 2022 2022 Citations: 29
Additional trunk training improves sitting balance following acute stroke: a pilot randomized controlled trial V Kumar, K Babu, A Nayak International Journal of Current Research and Review 2 (3), 26-43 , 2011 2011 Citations: 28
Soil fertility evaluation for macronutrients using parkers nutrient index approach in some soils of varanasi district of eastern Utter Pradesh, India SP Singh, S Singh, A Kumar, R Kumar International Journal of Pure and Applied Bioscience 6 (5), 542-548 , 2018 2018 Citations: 27
Callus induction and plant regeneration in Solanum tuberosum L. cultivars (Kufri Chipsona 3 and MP-97/644) via leaf explants V Kumar, D Rashmi, M Banerjee International Research Journal of Biological Sciences 3 (6), 66-72 , 2014 2014 Citations: 26
Multi-tasking of SERK -like kinases in plant embryogenesis, growth, and development: current advances and biotechnological applications V Kumar, J Van Staden Acta Physiologiae Plantarum 41 (3), 31 , 2019 2019 Citations: 24
Bayesian analysis of exponential extension model V Kumar J. Nat. Acad. Math 24, 109-128 , 2010 2010 Citations: 23
A review of Swertia chirayita (Gentianaceae) as a traditional medicinal plant. Front Pharmacol 6: 308 V Kumar, J Van Staden 2015 Citations: 22
