Transformer-based neural optimization for energy-efficient event detection in wide-area power monitoring systems Eatedal Alabdulkreem, Wahida Mansouri, K. K. Deepika, Mohammed A. AlAqil, Mohammed Abaker, M. Kavitha, V. Priya, Raj Kumar Masih International Journal of Information Security, 2026 The security and stability of modern power systems rely heavily on timely and accurate detection of anomalies, including cyberattacks. Traditional anomaly detection approaches often struggle to capture complex interdependencies among system components, resulting in decreased detection performance. In this study, we propose a novel deep learning-based method for detecting anomalous events in power networks. The proposed model leverages historical and real-time measurement data to identify deviations that indicate potential false data injection attacks. Extensive experiments were conducted on standard IEEE test systems, incorporating adversarially injected cyberattack signals to evaluate the robustness of the approach. The results demonstrate superior performance in accuracy, precision, and recall compared with conventional autoencoder-based models. This method provides a reliable tool for enhancing the cybersecurity and operational reliability of power systems.
Low Voltage Ride through Scheme for DFIG based Wind Energy Conversion System using Enhanced Demagnetization Control Subhendu Sekhar Sahoo, Trinadha Burle, Bevara Srikanth, K.K. Deepika, Ankit Garg 2025 IEEE 2nd International Conference on Green Industrial Electronics and Sustainable Technologies Giest 2025, 2025 Doubly fed induction generator (DFIG) is the utmost desired wind energy generator (WEG) in the last eras due to its high productivity and widespread speed operation. However, the direct linking of the grid with the stator terminal makes the system more prone to grid disturbances. Uncertainty issues like over-voltage in DC-Link capacitor, over-current in rotor winding, over-current in the stator winding, and electromagnetic torque oscillations deteriorate the system performances, leads to shutdown of the system. These uncertainties should be well kept within the safety limit under any severe voltage dip circumstances. An enhanced demagnetization control strategy has been proposed in this paper to accomplish these uncertainties. The proposed control scheme accelerates the efficacy of the traditional demagnetization control, able to grip under severe condition, unlike the traditional demagnetization scheme. Due to lower stator circuit time constant faster damping of stator natural flux is occurred. Faster is the damping performance; lesser will be the rotor electromotive force (EMF) generated in the rotor circuit. The reduced rotor EMF induced results all the fault consequences to be within their allowable limits. Thus reveals the effectiveness of the proposed enhanced demagnetisation control scheme, the simulation result is compared with the traditional demagnetisation control scheme and conventional vector scheme as well. Simulation of the proposed scheme is carried out using MATLAB/SIMULINK.
Pixhawk controlled quadcopter: enabling autonomous surveillance using telemetry for effective monitoring K. K. Deepika, P. Sai Rohan, S. Dileep Kumar, S. Khwaja Moinuddin, Pavani, R. S. Ravi Sankar Advances in Electronics Computer Physical and Chemical Sciences, 2025 The use of self-navigating surveillance drones that have been programmed to follow different routes has shown considerable improvements in surveillance capabilities. The performance of these drones was assessed in this study, and significant results were found. With a speed of 9.82 m/s, the unmanned aerial vehicles (UAVs) demonstrated its ability to operate quickly and effectively. Test path analysis revealed very few differences when compared to manual operations, taking an average of two minutes to complete the path. Furthermore, in autopilot mode, the Pixhawk flight controller demonstrated better stabilization. The RTL interruption test revealed a path spline deviation that altered the UAV’s return-to-launch trajectory. These findings highlight how autonomous surveillance drones can improve operational effectiveness and surveillance coverage. Because flexibility in different paths is provided, it is possible to thoroughly scan large areas in a short amount of time, optimizing the effectiveness of surveillance. Adaptive path-following and real-time data transmission improve operational dependability and situational awareness even more. As a result, autonomous surveillance drones offer a flexible and affordable option for a range of uses, such as emergency response, infrastructure monitoring, and border security. All things considered, the incorporation of autonomous surveillance drones with a variety of paths represents a major advancement in surveillance technology, providing unmatched capacity for productive and successful monitoring in a range of operational scenarios.
Zero-Emission Heavy-Duty, Long-Haul Trucking: Obstacles and Opportunities for Logistics in North America Paul D. Larson, Robert V. Parsons, Deepika Kalluri Logistics, 2024 Background: Pressure is growing in North America for heavy-duty, long-haul trucking to reduce greenhouse gas (GHG) emissions, ultimately to zero. With freight volumes rising, improvement depends on zero-emissions technologies, e.g., battery electric vehicles (BEVs) and fuel cell electric vehicles (FCEVs). However, emissions reductions are constrained by technological and commercial realities. BEVs and FCEVs are expensive. Further, BEVs depend on existing electricity grids and FCEVs rely on steam–methane reforming (SMR) or electrolysis using existing grids to produce hydrogen. Methods: This study assembles publicly available data from reputable sources to estimate breakeven vehicle purchase prices under various conditions to match conventional (diesel) truck prices. It also estimates GHG emissions reductions. Results: BEVs face numerous obstacles, including (1) limited range; (2) heavy batteries and reduced cargo capacity; (3) long recharging time; and (4) uncertain hours-of-service (HOS) implications. On the other hand, FCEVs face two primary obstacles: (1) cost and availability of hydrogen and (2) cost of fuel cells. Conclusions: In estimating emissions reductions and economic feasibility of BEVs and FCEVs versus diesel trucks, the primary contributions of this study involve its consideration of vehicle prices, carbon taxes, and electricity grid capacity constraints and demand fees. As electricity grids reduce their emissions intensity, grid congestion and capacity constraints, opportunities arise for BEVs. On the other hand, rising electricity demand fees benefit FCEVs, with SMR-produced hydrogen a logical starting point. Further, carbon taxation appears to be less important than other factors in the transition to zero-emission trucking.
A Smart ANN-Based Converter for Efficient Bidirectional Power Flow in Hybrid Electric Vehicles R.S.Ravi Sankar, Keerthi Deepika.K, Mohammad Alsharef, Basem Alamri Electronics Switzerland, 2022 Electric vehicles (EV) are promising alternate fuel technologies to curtail vehicular emissions. A modeling framework in a hybrid electric vehicle system with a joint analysis of EV in powering and regenerative braking mode is introduced. Bidirectional DC–DC converters (BDC) are important for widespread voltage matching and effective for recovery of feedback energy. BDC connects the first voltage source (FVS) and second voltage source (SVS), and a DC-bus voltage at various levels is implemented. The main objectives of this work are coordinated control of the DC energy sources of various voltage levels, independent power flow between both the energy sources, and regulation of current flow from the DC-bus to the voltage sources. Optimization of the feedback control in the converter circuit of HEV is designed using an artificial neural network (ANN). Applicability of the EV in bidirectional power flow management is demonstrated. Furthermore, the dual-source low-voltage buck/boost mode enables independent power flow management between the two sources—FVS and SVS. In both modes of operation of the converter, drive performance with an ANN is compared with a conventional proportional–integral control. Simulations executed in MATLAB/Simulink demonstrate low steady-state error, peak overshoot, and settling time with the ANN controller.
Comparison of Principal-Component-Analysis-Based Extreme Learning Machine Models for Boiler Output Forecasting K. K. Deepika, P. Srinivasa Varma, Ch. Rami Reddy, O. Chandra Sekhar, Mohammad Alsharef, Yasser Alharbi, Basem Alamri Applied Sciences Switzerland, 2022 In this paper, a combined approach of Principal Component Analysis (PCA)-based Extreme Learning Machine (ELM) for boiler output forecasting in a thermal power plant is presented. The input used for this prediction model is taken from the boiler unit of the Yermarus Thermal Power Station (YTPS), India. Calculation of the accurate electrical output of a boiler in an operating system requires the knowledge of hundreds of operating parameters. The dimensionality of the input dataset is reduced by applying principal component analysis using IBM@SPSS Software. In the process of principal component analysis, a dataset of 232 parameters is standardized into 16 principal components. The total dataset collected is divided into training and testing datasets. The extreme learning machine is designed for various activation functions and the number of neurons. Sigmoid and hyperbolic tangent activation functions are studied here. Its generalization performance is examined in terms of the Mean Square Error (MSE), Mean Absolute Error (MAE), Root Mean Square (RMSE), and Mean Absolute Percentage Error (MAPE). ELM and PCA–ELM are compared. In both the ELM and PCA–ELM models, when the extreme learning machine was designed with a sigmoid activation function with 100 nodes in the hidden layer, RMSE was 5.026 and 4.730, respectively. Therefore, the developed combined approach of PCA–ELM proved as a promising technique in forecasting with reduced errors and reduced time.
Energy Efficient Photovoltaic-Electric Spring for Real and Reactive Power Control in Demand-Side Management Keerthi Deepika Kollipara, J. Vijay Kumar, Prasanthi R, Srinivasa Rao Sura, M. S. Pradeep Kumar Patnaik, R. S. Ravi Sankar Frontiers in Energy Research, 2022 Photovoltaic-electric spring (PV-ES) is a promising topology to utilize widespread residential roof-top photovoltaic systems in demand-side management. Power control for an integrated configuration of photovoltaic-electric spring system to achieve dynamic supply-demand balance in power distribution networks is presented. Extraction of maximum power from PV panel using Perturb and Observe algorithm along with boost converter are designed. This power is given as input to the DC link of the Electric Spring. The modeling and design of the integrated system are detailed. Extensive simulations are carried out in MATLAB/Simulink to observe the performance of the PV-ES system. The effectiveness of the proposed topology was verified for changes in line voltage, PV irradiation, and reference power. It was confirmed that the proposed PV-ES precisely controls the active power consumption of the critical load, rigidly regulates the voltage at the point of common coupling (PCC), and follows the variations in reference power available for the smart load. Finally, the expansive performance of ES fed with a PV source was confirmed to be superior over an ES system fed with a DC source.
Design of Back-to-Back Converter Interface for Electric Spring in a Distribution System K. K. Deepika, J. Vijaya Kumar, Srinivasa Varma Pinni, Srinivasa Rao Sura, R. S. Ravi Sankar Frontiers in Energy Research, 2022 In a distribution system, the erratic output power of distributed generation causes fluctuations in the available power to critical loads on the demand side. A novel electric spring (ES) with back-to-back converter configuration is proposed. Besides PCC voltage regulation and power control, the proposed converter integrates the ES to the grid without compromising the DC link voltage and the quality of the grid current. It comprises an instantaneous DC link voltage control, active power control, PCC voltage control, and a hysteresis band current control. The systematic design of the parameters in the configuration is detailed. Simulations were performed in MATLAB/Simulink, and a series of comparative analyses at various control stages were demonstrated. The quality of the grid current was analyzed with PI, PR, and hysteresis band current controllers. It was established that the hysteresis band current controller gave the best performance. Similarly, the DC link voltage was efficiently regulated with the instantaneous DC link voltage controller than the conventional controller.
