Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
Search Results
Item Investigation and Performance Evaluation of Novel Single-Switch High-Gain DC-DC Converters for DC Microgrid Applications(Institute of Electrical and Electronics Engineers Inc., 2025) Diwakar Naik, M.; Vinatha Urundady, U.; Naik, M.; Bonthagorla, P.K.This paper introduces a novel single-switch, non-isolated high-gain DC-DC converter for solar photovoltaic (PV) and fuel-cell (FC) applications. These energy sources typically provide a continuous supply of current, necessitating a high-gain DC-DC converter that operates in continuous conduction mode (CCM). This converter draws a continuous input current from the supply and delivers a continuous output current to the load. The performance of the converter is thoroughly analyzed through the development of a state-space model and the derivation of the small signal transfer function, which helps in understanding the converter’s dynamic behavior. Detailed comparisons with existing converters are also presented. Furthermore, an output voltage controller is designed using the k-factor method to effectively regulate the output voltage without requiring a current sensor, even in the presence of input voltage variations. To validate the effectiveness of the converter and its controller, a 150 W prototype was constructed and experimentally verified in a laboratory setting. © 2013 IEEE.Item Smart Strategies for Improving Electric Vehicle Battery Performance and Efficiency(Nature Research, 2025) Tangi, S.; Vatsa, A.; Opam, A.; Bonthagorla, P.K.; Gaonkar, D.N.The increasing demand for Electric Vehicles (EVs) necessitates accurate range prediction and optimization of driving parameters to address range anxiety and improve user experience. This study proposes a machine learning-based framework for predicting EV range, optimum acceleration, and velocity using a synthetically generated dataset of 2,000 samples designed to reflect real-world driving scenarios. Four models—Random Forest (RF), Extra Trees (ET), Linear Regression (LR), and Long Short-Term Memory (LSTM)—were evaluated individually and in ensemble combinations. To ensure statistical reliability, all models were trained and tested over ten independent runs with randomized data partitions, and the results were reported as average performance with standard deviations. The ensembles consistently outperformed individual models, with the full ensemble (RF + ET + LSTM + LR) achieving the most robust performance across all metrics (MAE, MSE, and R²). Furthermore, a real-time web application was developed using the trained models to dynamically estimate driving parameters. The findings highlight the potential of integrating AI-driven predictive modelling into EV systems to support efficient driving behaviour and energy management. © The Author(s) 2025.