Cyber-physical systems (CPSs) are vulnerable to cyber-attacks. Nowadays, the detection of cyber-attacks in microgrids as examples of CPS has become an important topic due to their wide use in various practical applications, from renewable energy plants to power distribution and electric transportation. In this paper, we propose a new artificial intelligence (AI)-based method for detection of cyber-attacks in direct current (DC) microgrids and also identification of the attacked distributed energy resource (DER) unit. The proposed method works based on time series analysis and a nonlinear auto-regressive exogenous model (NARX) neural network, which is a special type of recurrent neural network, for estimating DC voltages and currents. In the proposed method, we consider the effect of cyber-attacks named false data injection attacks (FDIAs), which try to affect the accurate voltage regulation and current sharing by affecting voltage and current sensors. In the presented strategy, first, a DC microgrid is operated and controlled without any FDIAs to gather enough data during the normal operation required for the training of NARX neural networks. It is worth mentioning that, in the data generation process, load changing is also considered to have distinguishing datasets for load changing and cyber-attack scenarios. Trained and fine-tuned NARX neural networks are exploited in an online manner to estimate the output DC voltages and currents of DER units in DC microgrid. Then, based on the error of estimation, the cyber-attack is detected. To show the effectiveness of the proposed method, offline digital time-domain simulation studies are performed on a test DC microgrid system in MATLAB/Simulink environment, and the results are verified using real-time simulations using OPAL-RT real-time digital simulator (RTDS).

Direct current (DC) microgrids can be considered as cyber-physical systems due to implementation of measurement devices, communication network, and control layers. Consequently, dc microgrids are also vulnerable to cyber-attacks. False-data injection attacks (FDIAs) are a common type of cyber-attacks, which try to inject false data into the system in order to cause the defective behavior. This article proposes a method based on model predictive control (MPC) and artificial neural networks (ANNs) to detect and mitigate the FDIA in dc microgrids that are formed by parallel dc–dc converters. The proposed MPC/ANN-based strategy shows how MPC and ANNs can be coordinated to provide a secure control layer to detect and remove the FDIAs in the dc microgrid. In the proposed strategy, an ANN plays the role of the estimator to implement in the cyber-attack detection and mitigation strategy. The proposed method is examined under different conditions, physical events and cyber disturbances (i.e. load changing and communication delay, and time-varying attack), and the results of the MPC-based scheme is compared with conventional proportional-integral controllers. The obtained results show the effectiveness of the proposed strategy to detect and mitigate the attack in dc microgrids.

DC microgrids can be considered as cyber-physical systems (CPSs) and they are vulnerable to cyberattacks. Therefore, it is highly recommended to have effective plans to detect and remove cyberattacks in dc microgrids. This article shows how artificial neural networks can help to detect and mitigate coordinated false data injection attacks (FDIAs) on current measurements as a type of cyberattacks in dc microgrids. FDIAs try to inject the false data into the system to disrupt the control application, which can make the dc microgrid shutdown. The proposed method to mitigate FDIAs is a decentralized approach and it has the capability to estimate the value of the false injected data. In addition, the proposed strategy can remove the FDIAs even for unfair attacks with high domains on all units at the same time. The proposed method is tested on a detailed simulated dc microgrid using the MATLAB/Simulink environment. Finally, real-time simulations by OPAL-RT on the simulated dc microgrid are implemented to evaluate the proposed strategy.

Because of the existence of communication networks and control applications, DC microgrids can be attacked by cyber-attackers. False data injection attack (FDIA) is one type of cyber-attacks where attackers try to inject false data to the target DC microgrid to destruct the control system. This work discusses the effect of FDIAs in DC microgrids that are structured by parallel DC/DC converters and they are controlled by droop based control strategies to maintain the desired DC voltage level. Also, an effective and proper strategy based on an artificial neural network-based reference tracking application is introduced to remove the FDIAs in the DC microgrid.

Over the past decade, the high penetration of renewable-based distributed generation (DG) units has witnessed a considerable rise in electrical networks. In this context, direct current (DC) microgrids based on DGs are being preferred due to having less complexity for the establishment and control. At the same time, they offer higher efficiency and reliability compared to their alternating current (AC) counterparts. This paper proposes a new model predictive control (MPC)-trained artificial neural network (ANN) control strategy being an ANN-MPC instead of conventional cascaded-proportional-integral (PI)-trained ANN control for dynamic damping of photovoltaic (PV)-battery-based grid-connected DC microgrids. Unlike traditional controllers, the proposed control approach more rapidly attains generation-load power balancing under variable climate input (meteorological sensor data) and output (load demand), hence achieving quick DC-bus voltage damping. The proposed ANN-MPC scheme is examined under different operating conditions, and the results are compared with the ANN-based conventional PI controller. The results show the proposed control strategy's efficacy to lessen the instability issues and achieve effective attenuation of oscillations in DC microgrids.

DC microgrids can be operated under a hierarchical control strategy, and it needs a communication-based layer. The implementation of digital controllers and the communication infrastructure can make a dc microgrid vulnerable to cyber-attacks. This article introduces an approach based on Artificial Intelligence (AI) to detect and mitigate cyber-attacks in a dc microgrid. The proposed method is based on the artificial neural network (ANN), which can be categorized as an AI-based method. The proposed application implements an ANN to detect and mitigate false data injection attacks (FDIAs). FDIAs try to inject false data into the system to affect the control application of the dc microgrid, and it can shut down the dc microgrid. The proposed method can calculate the value of the false data, and it can detect and remove the attack simultaneously. The proposed method is tested in a MATLAB/Simulink environment. Also, to have more accurate results, the introduced approach is examined under different conditions and cyber/physical disturbances (e.g., communication delay, noise, plug-and-play of additional units, and time-varying FDIAs). Besides, a comparison is considered to evaluate the effectiveness of the proposed strategy. The obtained results can conclusively prove the effectiveness, accuracy, and authenticity of the proposed method to successfully detect the FDIAs and remove the cyber-attack.