The importance of and need for cyber security have increased in the last decade. The critical infrastructure of the country, modeled with cyber-physical systems (CPS), is becoming vulnerable because of a lack of efficient safety measures. Attackers are becoming more innovative, and attacks are becoming undetectable, thereby causing huge risks to these systems. In this scenario, intelligent and evolving detection methods should be introduced to replace basic and outworn methods. The ability of artificial intelligence (AI) to analyze data and predict outcomes has created an opportunity for researchers to explore the power of AI in cyber security. This article discusses new-age intelligence and smart techniques such as pattern recognition models, deep neural networks, generative adversarial networks, and reinforcement learning for cyber security in CPS. The differences between the traditional security methods used in information technology and the security methods used in CPS are analyzed, and the need for a transition into intelligent methods is discussed in detail. A deep neural network-based controller that detects and mitigates cyber attacks is designed for microgrid systems. As a case study, a stealthy local covert attack that overcomes the existing microgrid protection is modeled. The ability of the DNN controller to detect and mitigate the SLCA is observed. The experiment is performed in a simulation and also in real-time to analyze the effectiveness of AI in cyber security.

A continuous change in the solar irradiance level and local atmospheric conditions, such as temperature and humidity, necessitate the use of maximum power point tracking (MPPT) technique of a photovoltaic (PV) system. MPPT ensures to harvest maximum power. Generally, voltage and current sensors are required to track the power of a PV system. The proposed method tracks the power of a PV system without the use of any current sensor. It not only reduces the cost of the system, but also reduces the communication burden, internal disturbances, and complexity. The proposed scheme estimates the current internally by using Luenberger observer technique. Thus, the estimated current is given to perturb and observe based MPPT technique, to generate the required duty for a dc–dc boost converter. The proposed scheme is experimentally investigated, and thus, obtained results are compared with well-established MPPT techniques. A comparison shows that the proposed system results are in a good agreement with the current sensor based MPPT technique.

The increase in the numbers of electric vehicles (EVs) is seen as an upgrading of the existing vehicles for various reasons. This calls for an in‐depth analysis of the heart of these vehicles—the motor. A motor in an electric vehicle propulsion system is a crucial component that has the ability to affect the efficiency, weight, cost, reliability, power output and performance. Hence a detailed comparative study, that compares the existing types and topologies of various motors, is the need of the hour. The various motors that can be used in electric traction, namely DC, induction, switched reluctance, permanent magnet brushless AC motors and permanent magnet brushless DC motors, are reviewed in view of their capabilities with respect to EV propulsion. A detailed review is presented of existing motors and the application of power electronic techniques to EVs, and recommendations for some new designs of brushless DC motors. These include permanent magnet hybrid motors, permanent magnet spoke motors and permanent magnet inset motors.

DC microgrids (DCMGs) are evolving into cyber-physical systems with advanced communication networks and computational methodologies, making them sensitive to cyber-attacks. These attacks can threaten the safe operation of a system. In this article, a virtual sensor-based framework is proposed for continuously monitoring and detecting malicious activities at the hardware level of a DCMG system. An adaptive state observer with a low computational burden is designed to estimate the voltage and current of a dc–dc converter. The proposed method considers the effects of cyber-attacks by injecting false data (FD) at targeted nodes in an attempt to affect the voltage regulation and current sharing by modifying the onboard voltage and current sensors. In the presented strategy, first, a DCMG is operated and controlled without any false data injecting attacks with different load conditions. Next, the DCMG is exposed to various cyber-attacks, and the output voltages and currents of dc–dc converters are estimated. Based on the error between the estimated and actual sensed signals, the cyber-attack is detected and corrected with the proposed framework. The proposed scheme is simple in design, efficient in operation, and easily implemented in a distributed control system. The effectiveness and robustness of the proposed method are illustrated by implementing it in real-time hardware using the LabView test bench by considering four dc systems (including a solar photovoltaic system) connected in a ringlike manner communicated via an ethernet-based local area network.