Power electronic converters have become an integral part of the direct current microgrid (DCMG) systems. The efficient control of these converters will decide the performance of the DC microgrids. With the evolution of cyber physical systems, all these power converters are integrated into the communication networks to achieve intelligent and smart control. Data in the communication networks are highly vulnerable towards cyber-attacks, leaving it unaddressed will lead to substantial economic losses and disasters. This article proposes a standalone implementation of multi-deep neural network (MDNN) based DC-DC converter and its application to detect false data injection (FDI) attacks at the sensor level. A MDNN is developed with a combination of deep neural network (DNN) and error detection network (EDN). DNN is used as the controller to achieve closed loop operation of DC-DC converter and EDN is used to detect and mitigate the FDI attack. Initially, proposed scheme is executed in MATLAB simulink platform with various disturbances at controller level and several attack scenarios are verified with its experimental results.
1 April 2024 in IEEE Transactions on Industry Applications
This article introduces a novel approach to enhance the cybersecurity of cyber-physical systems (CPS) by integrating a Hybrid Physics Informed Neural Network (HPINN) into the control framework of a DC-DC converter. The proposed system leverages the strengths of both physics-based modeling and datadriven techniques to detect and mitigate false data injection attacks (FDIA) affecting the converter's performance. This article proposes a novel HPINN based methodology for FDIA attack detection and mitigation. The proposed methodology includes the design of PINN based attack detection module and PINN prediction module, the combination of these two modules ensures robust control during system uncertainties and reliable operation during FDIA scenarios. PINN detection module is a combination of state estimator and NN classifier. The article presents the architecture of the hybrid system and details its training process, emphasizing the integration of physical principles to enhance the model's interpretability and generalization. Simulation is performed in MATLAB Simulink 2023b; Simulation results demonstrate the effectiveness of the proposed approach in detecting and mitigating FDIA, including those attempting to manipulate the converter's output or compromise its stability. Later, real-time implementation of the proposed method is performed by developing experimental hardware and deploying the HPINN model into the Atmel SAM3X8E ARM Cortex-M3 microcontroller. The proposed scheme is analyzed for various scenarios like load changes, constant FDIA, and time-varying FDIA and its results are explored.
27 May 2025 in IEEE Journal of Emerging and Selected Topics in Power Electronics
As the transition to green and sustainable energy accelerates, integrating renewable energy sources into DC microgrids (DC MGs) is becoming increasingly essential. However, ensuring efficient control performance while addressing cybersecurity threats remains a critical challenge. Communication links and sensors in DC MG are highly vulnerable to False Data Injection (FDI) attacks, yet cyber threat mitigation is often overlooked in control design. This study proposes a Hybrid Physics-Informed Neural Network (HPINN) methodology that integrates Linear Kalman Filters (LKF) with neural networks (NNs) to enhance cyber-attack detection and mitigation. Unlike conventional LKF, which lacks inherent attack mitigation capability, HPINN leverages NN-based correction to ensure robust state estimation and secure control operations. The proposed approach is validated on a supervisory-controlled 3-bus DC MG with a ring main connection, comprising a fuel cell and battery (node 1), a photovoltaic (PV) system and battery (node 2), and another PV system and battery (node 3). The performance is evaluated through MATLAB Simulink simulations and a real-time experimental setup, incorporating source changes, load variations, and FDI attack scenarios. Results demonstrate that HPINN effectively detects and mitigates cyber-attacks, ensuring accurate DC MG operation even under compromised sensor measurements. This work provides a scalable and secure control strategy, reinforcing the resilience of next-generation smart microgrids.
With the growing reliance on DC microgrids (DC MGs) in critical infrastructure, securing them against sophisticated cyberattacks is essential. This study presents a hybrid cyber-defense (HCD) framework that detects and mitigates false data injection (FDI) and replay attacks through a combination of bidirectional LSTM (Bi-LSTM) autoencoders for anomaly detection, cross-correlation analysis for replay attack identification, and a physics-informed neural network (PINN) for adaptive control. A Kalman filter-based estimator maintains control stability when sensor measurements are compromised. The framework operates in a fully decentralized manner at the local controller level, enabling fast, low-latency responses. Validation on a 4-bus MATLAB/Simulink model and a 3-bus DC MG experimental testbed demonstrates over 95% detection accuracy and effective mitigation, preserving voltage stability under attack. The proposed control algorithm is deployed in the AT19SAM3X8E microcontroller, acting as the local controller at each node, occupying 40 $KB$ of memory with an execution time of 0.4 $ms$. This real-time deployment confirms practical applicability for lightweight, standalone operation. These results demonstrate the proposed method’s robustness and scalability, advancing intelligent, real-time cyber-resilience for future DC MG.
5 November 2024 in IEEE Industry Applications Magazine
Solar Photovoltaic (SPV) systems can exhibit multiple local maxima in their current-voltage (I-V) and power-voltage (P-V) characteristics due to partial shading at the panel or string level. The frequent occurrence and prolonged operation of panels under partial shading conditions may lead to a reduction in power output and hot-spot formation on the panels. Early detection and exact identification of these shaded panels can significantly reduce power losses and prevent hot spots. In this regard, this article proposes a novel method that utilizes multi-capacitorbased I-V and P-V techniques to determine the exact location of the shaded panels. The proposed I-V and P-V technique includes an additional hardware module (AHM) that generates the I-V and P-V curves of the SPV string, which are fed to an artificial intelligence (AI) based classification model through the sensor and control unit. The dual-phase classification algorithm is designed with a convolution neural network (CNN) to classify between normal and faulty panels. CNN model sends the relevant information about the faulty panel to the plant controller, which remotely bypasses the panel to prevent any physical damage and losses in the SPV system. The proposed method is realized in real-time by developing an experimental setup with a solar farm and AHM module. The IV and PV curves of the proposed system under different shading scenarios are explored.