Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
Search Results
Item Anomalous Electrical Power Consumption Detection in Household Appliances via Micro-Moment Classification(Institute of Electrical and Electronics Engineers Inc., 2025) Nayak, R.; Jaidhar, C.D.The detection of anomalous power consumption is critical for improving energy efficiency, particularly with the increasing demand in buildings. This study explores Convolutional Neural Network-based models by transforming 1-dimensional micro-moment labeled data into 2-dimensional matrices to capture both temporal and spatial consumption patterns. Three architectural variants are investigated: a conventional Deep Convolutional Neural Network (DCNN), a Depthwise Separable Convolutional Neural Network (DS-CNN), and a Depthwise Separable Residual Convolutional Neural Network (DSR-CNN). Unlike earlier studies, this work incorporates hyperparameter tuning, statistical validation, and cross-validation, resulting in the evaluation of over 450 model configurations. The results indicate that while the DCNN consistently achieves the highest accuracy, the DS-CNN achieves comparable performance with significantly reduced parameters and computational cost, making it suitable for real-time and resource-constrained environments. Model complexity analysis and statistical tests confirm the robustness of the findings. Finally, a systematic model selection strategy is presented, identifying the DS-CNN as the most balanced solution for effective and efficient anomaly detection in smart grid applications. © 2020 IEEE.Item Enhanced flexibility and performance of interdigitated microsupercapacitors through in-situ rGO growth in NiCuSe nanocomposite conductive ink(Elsevier Ltd, 2025) Saquib, M.; Nayak, R.; Muthu, M.; Bhat, D.K.; Rout, C.S.Microsupercapacitors (MSCs) are promising alternative power sources capable of meeting the growing demand for wearable and on-chip electronics due to their compact size, lightweight nature, exceptional charge-discharge rates, high power densities, and superior flexibility. However, a major challenge in current MSCs development lies in their limited energy density, high-cost, and time-intensive fabrication processes. This study focuses on fabricating flexible interdigitated printed MSCs using in-situ growth of reduced graphene oxide within nickel-copper selenide nanocomposite inks via screen printing. The eco-friendly ink formulation incorporates ethyl cellulose, diacetone alcohol, and a non-ionic surfactant to optimize printability, viscosity, and post-drying efficacy. The MSCs achieved a high areal capacitance of 756.3 mFcm?2 at 5 mVs?1, with energy densities of 84.4 µWcm?2 (symmetric) and 151.2 µWhcm?2 (asymmetric), and corresponding power densities of 406 mW cm?² and 1210 mW cm?². The printed devices retained 94.2 % of their capacitance on PET (Polyethylene terephthalate) substrates and exhibited excellent mechanical stability under bending, making them ideal for wearable electronics and flexible IoT applications. These results highlight the potential of the fabricated screen-printed MSCs, leveraging the optimized electrode material, as a high-performance and eco-friendly energy storage technology for next-generation flexible electronics. © 2025 The AuthorsItem Data-driven models for electricity theft and anomalous power consumption detection: a systematic review(Springer, 2025) Nayak, R.; Jaidhar, C.D.To maintain the effectiveness, dependability, and security of modern energy systems, analyzing and detecting anomalies in energy usage, such as electricity theft and unusual power consumption, is crucial as Smart Grid (SG) technologies become increasingly common. This survey paper comprehensively reviews the literature on energy consumption analysis and detection, focusing on detecting electricity theft and anomalous power consumption. The works that are considered in this paper are classified based on Machine Learning (ML), Deep Learning (DL), and hybrid models, to identify electricity theft and unusual power usage. Privacy preservation-based methodologies in the context of energy consumption research and summarize the survey articles. Furthermore, datasets used in electricity theft and anomalous power consumption detection, applications, challenges, and limitations related to detecting abnormal power usage and electricity theft are also discussed, and suggested future research paths to push the boundaries of this field of work. This survey study offers a thorough overview of current research trends and directions in energy consumption analysis and detection by synthesizing ideas from various studies. It benefits researchers, practitioners, and policymakers in the energy sector. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.