Explore the vast range of titles available.

Smart grid (SG) systems are designed to leverage digital automation technologies for monitoring, control and analysis. As SG technology is implemented in increasing number of power systems, SG data becomes increasingly vulnerable to cyber‐attacks. Classic analytic physics‐model based bad data detection methods may not detect these attacks. Recently, physics‐model and data‐driven methods have been proposed to use the temporal aspect of the data to learn multivariate statistics of the SG such as mean and covariance matrices of voltages, power flows etc., and then make decisions based on fixed values of these statistics. However, as loads and generation change within a system, these statistics may change rapidly. In this study, an adaptive data‐driven anomaly detection framework, Ensemble CorrDet with Adaptive Statistics (ECD‐AS), is proposed to detect false data injection cyber‐attacks under a constantly changing system state. ECD‐AS is tested on the IEEE 118‐bus system for 15 different sets of training and test datasets for a variety of current state‐of‐the‐art bad data detection strategies. Experimental results show that the proposed ECD‐AS solution outperforms the related strategies due to its unique ability to capture and account for rapidly changing statistics in SG.

The aim of this paper is to study an adaptive neural finite-time resilient dynamic surface control (DSC) strategy for a category of nonlinear fractional-order large-scale systems (FOLSSs). First, a novelty fractional-order Nussbaum function and a coordinate transformation method are formulated to overcome the compound unknown control coefficients induced by the unknown severe faults and false data injection attacks. Then, an enhanced fractional-order DSC technology is employed, which can tactfully surmount the deficiency of explosive calculations exposed in the backstepping framework. Furthermore, the radial basis function neural network is applied to address the unknown items related to the nonlinear FOLSSs. Based on the fractional Lyapunov stability criterion, a decentralized finite-time control approach is developed, which can ensure that all states of the closed-loop system are bounded and that the stabilization errors of each subsystem tend toward a small area in finite time. At last, two simulation examples are given to confirm the put-forward control algorithm’s effectiveness.

Over the last decade, the number of cyber attacks targeting power systems and causing physical and economic damages has increased rapidly. Among them, false data injection attacks (FDIAs) are a class of cyber‐attacks against power grid monitoring systems. Adversaries can successfully perform FDIAs to manipulate the power system state estimation (SE) by compromising sensors or modifying system data. SE is an essential process performed by the energy management system towards estimating unknown state variables based on system redundant measurements and network topology. SE routines include bad data detection algorithms to eliminate errors from the acquired measurements, e.g. in case of sensor failures. FDIAs can bypass BDD modules to inject malicious data vectors into a subset of measurements without being detected, and thus manipulate the results of the SE process. To overcome the limitations of traditional residual‐based BDD approaches, data‐driven solutions based on machine learning algorithms have been widely adopted for detecting malicious manipulation of sensor data due to their fast execution times and accurate results. This study provides a comprehensive review of the most up‐to‐date machine learning methods for detecting FDIAs against power system SE algorithms.

The secure operation of smart grids is closely linked to state estimates that accurately reflect the physical characteristics of the grid. However, well-designed false data injection attacks (FDIAs) can manipulate the process of state estimation by injecting malicious data into the measurement data while bypassing the detection of the security system, ultimately causing the results of state estimation to deviate from secure values. Since FDIAs tampering with the measurement data of some buses will lead to error offset, this paper proposes an attack-detection algorithm based on statistical learning according to the different characteristic parameters of measurement error before and after tampering. In order to detect and classify false data from the measurement data, in this paper, we report the model establishment and estimation of error parameters for the tampered measurement data by combining the the k-means++ algorithm with the expectation maximization (EM) algorithm. At the same time, we located and recorded the bus that the attacker attempted to tamper with. In order to verify the feasibility of the algorithm proposed in this paper, the IEEE 5-bus standard test system and the IEEE 14-bus standard test system were used for simulation analysis. Numerical examples demonstrate that the combined use of the two algorithms can decrease the detection time to less than 0.011883 s and correctly locate the false data with a probability of more than 95%.

False data injection attacks (FDIAs) on sensor networks involve injecting deceptive or malicious data into the sensor readings that cause decision-makers to make incorrect decisions, leading to serious consequences. With the ever-increasing volume of data in large-scale sensor networks, detecting FDIAs in large-scale sensor networks becomes more challenging. In this paper, we propose a framework for the distributed detection of FDIAs in large-scale sensor networks. By extracting the spatiotemporal correlation information from sensor data, the large-scale sensors are categorized into multiple correlation groups. Within each correlation group, an autoregressive integrated moving average (ARIMA) is built to learn the temporal correlation of cross-correlation, and a consistency criterion is established to identify abnormal sensor nodes. The effectiveness of the proposed detection framework is validated based on a real dataset from the U.S. smart grid and simulated under both the simple FDIA and the stealthy FDIA strategies.

State estimation plays a vital role in the stable operation of modern power systems, but it is vulnerable to cyber attacks. False data injection attacks (FDIA), one of the most common cyber attacks, can tamper with measurement data and bypass the bad data detection (BDD) mechanism, leading to incorrect results of power system state estimation (PSSE). This paper presents a detection framework of FDIA for PSSE based on graph edge-conditioned convolutional networks (GECCN), which use topology information, node features and edge features. Through deep graph architecture, the correlation of sample data is effectively mined to establish the mapping relationship between the estimated values of measurements and the actual states of power systems. In addition, the edge-conditioned convolution operation allows processing data sets with different graph structures. Case studies are undertaken on the IEEE 14-bus system under different attack intensities and degrees to evaluate the performance of GECCN. Simulation results show that GECCN has better detection performance than convolutional neural networks, deep neural networks and support vector machine. Moreover, the satisfactory detection performance obtained with the data sets of the IEEE 14-bus, 30-bus and 118-bus systems verifies the effective scalability of GECCN.

Secure vehicular communication is a critical factor for secure traffic management. Effective security in intelligent transportation systems (ITS) requires effective and timely intrusion detection systems (IDS). In this paper, we consider false data injection attacks and distributed denial-of-service (DDoS) attacks, especially the stealthy DDoS attacks, targeting integrity and availability, respectively, in vehicular ad-hoc networks (VANET). Novel machine learning techniques for intrusion detection and mitigation based on centralized communications through roadside units (RSU) are proposed for the considered attacks. The performance of the proposed methods is evaluated using a traffic simulator and a real traffic dataset. Comparisons with the state-of-the-art solutions clearly demonstrate the superior detection and localization performance of the proposed methods by 78% in the best case and 27% in the worst case, while achieving the same level of false alarm probability.

In this paper, the consensus problem is investigated via sampled-data output feedback control for nonlinear multi-agent systems subject to output delay and false data injection attacks, where only the delayed sampling outputs are available. Firstly, employing the available information, an improved compensator that does not continuously communicate with neighbors is constructed to provide control signals. Secondly, in the absence and presence of false data injection attacks, two compensator-based sampled-data control protocols with different time-varying gains are put forward, respectively. Then, in combination with the Lyapunov–Krasovskii functional approach, the proposed protocols are capable of achieving consensus and compensating for the effect of output delay and attack signals. Furthermore, above results are extended to the multi-agent systems with more general nonlinearities. Particularly, the sampling period and the output delay are arbitrary positive constants, removing the constraints of upper bound. Finally, the feasibility of the proposed protocols is demonstrated by two practical simulations.

Power electronic converters are widely implemented in many types of power applications such as microgrids. Power converters can make a physical connection between the power resources and the power application. To control a power converter, required data such as the voltage and the current of that should be measured to be used in a control application. Therefore, a communication-based structure including sensors and communication links can be used to measure the desired data and transmit that to the controllers. So, a power converter-based system can be considered as a type of cyber-physical system, and it can be vulnerable to cyber-attacks. Then, it can strongly be recommended to use a strategy for a power converter-based system to monitor the system and identify the existence of cyber-attack in the system. In this study, artificial intelligence (AI) is deployed to calculate the value of the false data (i.e., constant false data, and time-varying false data) and detect false data injection cyber-attacks on power converters. Besides, to have a precise technical evaluation of the proposed methodology, that is evaluated under other issues, i.e., noise, and communication link delay. In the case of noise, the proposed strategy is examined under noises with different signal-to-noise ratios . Further, for the case of the communication delay, the system is examined under both symmetrical (i.e., same communication delay on all inputs) and unsymmetrical communication delays (i.e., different communication delay/delays on the inputs). In this work, artificial neural networks are implemented as the AI-based application, and two types of the networks, i.e., feedforward (as a basic type) and long short-term memory (LSTM)-based network as a more complex network are tested. Finally, three important AI-based techniques (regression, classification, and clustering) are examined. Based on the obtained results, this work can properly identify and calculate the false data in the system.

Addressed in this paper is the reachable set estimation (RSE) problem for fuzzy‐model‐based leader‐follower multi‐agent systems with time‐varying delays and false data injection attacks. First, the aperiodic sampled‐data control is designed for the follower agents with randomly occurring false data injection attacks. Then, using the Kronecker product, the error system between the leader and the follower is obtained in a compact general form. Next, a novel Lyapunov‐Krasovskii functional is constructed with the knowledge of sampling patterns and time‐varying delays. In the framework of linear matrix inequalities, sufficient consensus conditions are determined from the H∞ $H_\\infty$performance index and Lyapunov theory to guarantee that its reachable set is enclosed by an ellipsoid in the existence of bounded perturbations. In the end, the Duffing Van der Pol oscillator and the single‐link robot arm models are employed to validate the derived theoretical results. The reachable set estimation problem is considered for the first time for leader‐follower fuzzy MASs with time‐varying delays and bounded external disturbances. The aperiodic sampled‐data control is designed for all the follower agents with the information from the leader. Moreover, the Bernoulli distribution is used for modeling the randomly occurring false data injection attacks in the controller actuator channels. The proposed theoretical findings are validated by two practical examples, that is, Duffing Van der Pol oscillator and single‐link robot arm model.