False Data Detection Research Articles

Anomaly detection technique for securing microgrid against false data attacks

The development of microgrid automation depends on information and communication technologies, which are vulnerable to cyber-attacks. Recent advancements in MGs enhance power systems' efficacy and reliability, but cybersecurity remains a significant concern, especially with false data injection attacks (FDIAs) posing serious threats. FDIAs can compromise measurement devices and tamper with State Estimation (SE), risking the seamless operation of MGs. To address this, this paper proposes an efficient Iterative Free Detection of False Data (IFDFD) scheme for detecting FDIAs in microgrid state estimation. The IFDFD scheme uses complex Micro Phasor Measurement Unit (μPMU) measurements and computes nodal power injections to detect FDIAs. Furthermore, the proposed scheme integrates an S-Estimator to eliminate noise errors caused by environmental factors and the component lifespan, making IFDFD robust against sophisticated attackers. The proposed IFDFD scheme has been tested and validated on the modified IEEE 14 bus test system, integrating Distributed Generations (DGs). False data was injected into the measurements to test the scheme's effectiveness. The efficacy of proposed IFDFD scheme has been validated by comparing it to existing method of FDIAs. The obtained result clearly validates the efficacy of the proposed IFDFD scheme.

An unsupervised false data detection method based on graph autoencoder and attention network in power grid

An unsupervised false data detection method based on graph autoencoder and attention network in power grid

Enabling Efficient and Malicious Secure Data Aggregation in Smart Grid With False Data Detection

Enabling Efficient and Malicious Secure Data Aggregation in Smart Grid With False Data Detection

Deep Semi-Supervised Learning Method for False Data Detection Against Forgery and Concealing of Faults in Cyber-Physical Power Systems

This paper proposes a deep semi-supervised numerical false data detection (DSS-NFDD) method, where hidden data in labeled and unlabeled datasets are leveraged simultaneously, to detect the false data in CPPS. Two types of false data are considered in this study: one is the forged fault data, which makes operators mistakenly believe that there is a fault in their operating system; the other is the false data used to conceal actual faults. First, a data dimension reduction method is proposed based on the PageRank algorithm to avoid the excessive noise caused by high-dimension data. Then, a semi-supervised deep learning framework is established to detect false data samples, which consists of two parts: one is the priori estimation module, and the other is a false data scoring network. A novel concentration loss function is presented for training the false data scoring network, which minimizes the impacts of noise pollution and sample bias. Next, a false feature location method is proposed to help human operators eliminate anomalies. Finally, the effectiveness and the superiorities of the proposed DSS-NFDD method are verified by analyzing the simulation results for the IEEE-39 bus and IEEE-118 bus systems.

Cyber-secure energy and flexibility scheduling of interconnected local energy networks with introducing an XGBoost-assisted false data detection and correction method

The growing penetration of renewable energy resources (RERs) and the ever-increasing implementation of information and communication technologies in smart grids necessitate the utilization of fast and safe operation methods. These schemes should be able to cope with the intermittency of uncertain RERs and fully explore the capabilities of new technologies while considering the vulnerabilities as a result of digitalization. Here, the integrity of the energy and flexibility scheduling and trading heavily depends on the security of the cyber-physical system. Local energy networks (LENs) are introduced to easily incorporate and utilize distributed energy resources, improving electrical power reliability and efficiency. This study develops a cyber-secure energy and flexibility scheduling platform for interconnected local energy networks. Hence, it introduces a novel false data detection and correction method based on the XGBoost machine learning method and investigates the performance of the proposed algorithm in the context of an interconnected local energy network and the corresponding energy and flexibility transactions. In this regard, this paper initially presents a bilevel energy and flexibility scheduling problem for interconnected local energy networks (ILENs) considering cyber-attacks (BLEFSCAILEN), which tries to satisfy the energy and flexibility requirements of the ILEN guaranteeing a resilient decision against false data injection cyber-attacks. Within the proposed BLEFSCAILEN a bi-level multi-objective optimization problem is defined where the operator of ILEN optimizes both energy and flexibility trading among LENs in the upper level to maximize its revenue. In the proposed structure, the operator of each LEN is situated at the lower level and tries to minimize the scheduling cost and simultaneously maximize the local flexibility index. Furthermore, in order to evaluate and improve the proposed system’s cyber-security, a false data injection attack is constructed using the Gaussian probability distribution function. Herein, the scheduling of ILEN is optimized considering vulnerabilities of electricity consumption data as a consequence of cyber-attack. Finally, the novel XGBoost-assisted deviation bound-based false data detection/correction (XGBFDD) algorithm is suggested to mitigate the above-mentioned cyber-attack and attain near real-world conditions. Simulation results demonstrate that the proposed false data detection/correction strategy exhibits a maximum accuracy of 91.67 precent in mitigating the attack effects. This is because the acquired post-correction results exhibit minor deviations in comparison to the original optimization output that is calculated with the pre-attack consumption data.

Temporal false data injection attack and detection on cyber‐physical power system based on deep reinforcement learning

AbstractFalse data injection (FDI) attacks are serious threats to a cyber‐physical power system (CPPS), which may be launched by a malicious software or virus accessing only the measurements from one substation. This study proposes a novel attack method named the temporal FDI (TFDI) attack. Namely, the virus makes decisions based on temporal observations of the CPPS, and the attack is driven by a deep Q network (DQN) algorithm. As DQN takes vectors of continuous variables as input states, the proposed method is free of the state space explosion problem, which helps the virus to learn the optimal attack strategy efficiently. Moreover, for adopting time‐series measurements as quasi‐dynamic observations, long short‐term memory cells are employed as a layer of the Q network. The TFDI attack enables the virus to discern trends of load variations and enhance the attack’s effectiveness. Meanwhile, a countermeasure is also presented to detect the proposed FDI attack. Binary classifiers are trained for each bus to detect suspicious local measurements according to their deviations from system‐state manifolds. When suspicious measurements are spotted frequently, the corresponding bus is believed to be under FDI attacks. Test cases validate the efficacy of the proposed FDI attack method as well as its countermeasure.

A new cyber-security approach for load frequency control of hybrid interconnected renewable power systems

Countries worldwide are embracing the trend toward smart grids, depending on advanced technology and communication networks. However, the smart grid is more vulnerable to cyberattacks than its traditional counterpart, especially the false data injection attack (FDIA), which aims to add false data into the transmitted signals to cause undesirable behavior. This article proposes a new scheme to detect and estimate the FDIA on load frequency control (LFC) of modern interconnected power systems considering renewable energy sources (RESs) and high voltage direct current (HVDC) link. The proposed scheme is based on the Kalman filter (KF) and artificial neural networks (ANNs). The KF is used to detect the FDIA in the transmitted system signals and indicates the possibility of an attack in each transmitted signal, where the role of ANNs is to estimate the transmitted signal before attacking. Hence, based on KF and ANNs, the proposed scheme can ensure the detection of false data and remove the attack simultaneously. The proposed cyber-security scheme is considered a thorough solution that can effectively reduce the impact of the FDIA on any of the four transmitted signals within the two-area interconnected power system, all while simulating the virtual inertia control strategy. The simulation results of the studied low-inertia interconnected power system are carried out using MATLAB/Simulink® software. The simulation results successfully demonstrate the proposed scheme's efficacy, accuracy, and acceptability to detect and eliminate the FDIA on the LFC of low-inertia interconnected power grids.

Experimental Validation of a Remedial Action via Hardware-in-the-Loop System Against Cyberattacks Targeting a Lab-Scale PV/Wind Microgrid

This paper experimentally validates the effectiveness of a primary/backup framework in preventing/mitigating the impacts of false data injection (FDI) cyberattacks targeting a lab-scale wind/photovoltaic (PV) microgrid. As the primary mecha-nism, an artificial intelligence-based false data detection algorithm is proposed to forecast the upcoming measurements and alert the operator about the accuracy of sensors readings, directly collected from the field devices. Given that some FDI attacks are designed to bypass the utilized detection methods, it is essential to be prepared for such circumstances. Hence, as the backup mechanism, a remedial action scheme (RAS) is also introduced to mitigate the impacts of such malicious cyberattacks and keep the functionality of the microgrid. The proposed framework (i.e., FDI model, detection approach, and remedial action scheme) is developed as a hardware-in-the-loop (HIL) testbed within the cyber-physical structure of the smart microgrid. The experimental results validate 1) the negative impacts of modeled FDI attacks on the lab-scale microgrid, 2) the effectiveness of the developed false data detection technique, and 3) the efficiency of the proposed RAS to keep the normal operation of the targeted microgrid when the detection system fails to recognize the attack.

A Real-Time Multistage False Data Detection Method Based on Deep Learning and Semisupervised Scoring Algorithms

This article proposes a real-time multistage data-driven method to detect false data injected by an intruder. The proposed method is based on an accurate load model constructed by deep neural networks (long short-term memory and gated recurrent unit) where historical demand along with extra weather features are employed to formulate the problem as a sequence of predictions and build an appropriate DNN model. A distinct feature of the proposed method that dramatically improves accuracy is hyperparameter optimization (e.g., dropout rate, batch size, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\beta _{1}$</tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\beta _{2}$</tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\alpha$</tex-math></inline-formula> ) based on cross-validation. Since hyperparameter optimization consumes enormous resources to analyze the different combinations of hyperparameters and causes out-of-memory problems, we have implemented our framework based on a parallel distributed computing technique on high-performance computer clusters. A variety of case studies are examined to find the best model. At the end of this step, the best model is employed as a base reference to a semisupervised scoring algorithm for the purpose of finding sequence of injected false data. To improve the detection efficiency, inter-range, pruning, and minimum score are added to the proposed methodology that suppress high false-positive rates. Several scenarios from a real-world dataset have been studied in this article, and the results demonstrate that the proposed method can be used to detect various types of attacks, including scaling, ramping, professional ramping, and random attacks, with a good performance score (i.e., recall, precision, and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$F1$</tex-math></inline-formula> score) for all of them. Furthermore, it can mitigate false data with the forecasted load values.

Static Detection of False Data in the Power Grid by Fusing Structure and Attributes of Node

Static Detection of False Data in the Power Grid by Fusing Structure and Attributes of Node

基于ELM状态预测的智能电网虚假数据检测

基于ELM状态预测的智能电网虚假数据检测

False Phasor Data Detection Under Time Synchronization Attacks: A Neural Network Approach

Phasor measurement units (PMUs) used in the smart grids are vulnerable to time synchronization attacks (TSA), whose attack target is the global positioning systems (GPS). The attacker manipulates phase measurements by sending deceptive GPS signals to introduce errors in state estimation, which can affect bus power flow calculation and economic dispatching of the power system. Considering the case of multiple attacked PMUs in AC, a novel false phase data detection method is proposed in this paper. The method uses “phase coding” to extract and encode the potential relationship between amplitude and phase angle, and then builds a TSAs detection model based on a vector neural network that learns the encoded relationship vectors through dynamic routing. Finally, simulation experiments are carried out on IEEE 9, 14, 30, and 118 bus systems and real measurements provided by a province in China. The results show that the proposed method achieves the best performance among the detection methods based on the learning model.

Graph-based detection for false data injection attacks in power grid

False data injection attack (FDIA) is the main network attack type threatening power system. FDIA affect the accuracy of data by modifying the measured values of measuring equipment. When the power grid topology has not changed, the data-driven detection method has high detection accuracy. However, the power grid topology changes when faults, maintenance or adjustment in power flow distribution occur in the power system. The data-driven detection method can not capture the spatial feature changes, and the detection accuracy decreases. Considering the changes of power grid topology, a false data detection method based on graph neural network is proposed in this paper, which extracts the spatial features of power grid topology information and operation data through gated graph neural network (GGNN). To enhance node representation in this method, the attention mechanism is adopted to assign aggregation weights to neighbor nodes. This method is tested on IEEE 14-bus and IEEE 118-bus systems. The experimental simulation results show that compared with other data-driven detection methods, the proposed method can significantly improve the detection accuracy under the changes of power grid topology.

Deep Learning Algorithms and Parallel Distributed Computing Techniques for High-Resolution Load Forecasting Applying Hyperparameter Optimization

Electrical load forecasting is one of the critical tasks that helps power utility companies in planning and operation as well as the energy managementsystem (EMS) in controlling and optimizing the power grid’s performance. It guarantees system adequacy and reliability by reducing the gap between supply and demand, and it bolsters cybersecurity by enabling false data detection and system security by predicting system peak load. This article aims to build an accurate long-term load forecasting model based on deep learning (DL) algorithms. Initially, big-data analytics and feature engineering are applied to the power load and weather historical data. Next, three different load forecasting models are developed based on three corresponding deep neural network models (DNN): the simple RNN, the long short term memory (LSTM), and the gated recurrent unit (GRU), respectively. To find an accurate DNN model, a two-step hyperparameter optimization is performed consisting of cross-validation. In the first step, the random search (RS) algorithm is employed to narrow the parameter search space to a smaller local one. In the second step, the grid search (GS) algorithm is used to find the best hyperparameters in the local area located by RS. However, the computational burden of the DNN training process is too high and may lead to out-of-memory (OOM) issues, especially when we are dealing with a big volume of data. To overcome this problem, we developed our Python program based on Tensorflow framework and implemented the framework on a high-performance computer cluster (HPCC). Then, different jobs are defined to employ parallel distributed computing (PDC) capability on the SIU BigDawg HPCC. To this end, all DNN hyperparameters (e.g., number of layers, neurons, dropout, batch size, epoch, learning rate, etc.) can be optimized and result in a comprehensive and accurate load forecasting model. Our proposed method, along with the programming framework, is evaluated on a real-world dataset. Among the three models developed and tested, the GRU, with load and weather as features, has demonstrated excellent performance and outperformed the other two models for long-term forecasting with the best metrics (i.e., MSE, MAPE, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$R^2$</tex-math></inline-formula> ) and daily error almost less than 1%. Also, our best model (optimized GRU) is compared with the other reported state-of-the-art models such as DBN, SVR, RM-LSTM, DM-GCNN, TCMS-CNN. It is demonstrated that the proposed framework yields a superior performance than the others.

Stochastic detection against deception attacks in CPS: Performance evaluation and game-theoretic analysis

In this paper, we consider a security problem of remote state estimation in cyber–physical systems (CPS). The state measurements of a dynamic process, obtained by wireless sensors, may be modified deceptively by a malicious attacker, which may bypass a standard χ2 detector. On the other hand, the estimation performance with a standard χ2 detector typically is also difficult to analyze. As such, a stochastic detection mechanism with a varying triggering threshold is proposed. We provide an analytical performance evaluation for the estimation with the proposed detector, and propose a potential countermeasure to actively defend the deception attacks with the proposed detector. The interactive decision-making process between the system with the countermeasure and the attacker is then studied under a game-theoretic framework. In addition, we also extend the stochastic false data detection problem into a multi-sensor setting with a sequential data fusion process and more general attacking patterns, and analyze the estimation performance. Simulations are provided to illustrate the developed results.

Detection and Prevention of False Data Injection Attacks in the Measurement Infrastructure of Smart Grids

The smart grid has become a cyber-physical system and the more cyber it becomes, the more prone it is to cyber-attacks. One of the most important cyber-attacks in smart grids is false data injection (FDI) into its measurement infrastructure. This attack could manipulate the control center in a way to execute wrong control actions on various generating units, causing system instabilities that could ultimately lead to power system blackouts. In this study, a novel false data detection and prevention paradigm was proposed for the measurement infrastructure in smart grids. Two techniques were devised to manage cyber-attacks, namely, the fixed dummy value model and the variable dummy value model. Limitations of the fixed dummy value model were identified and addressed in the variable dummy value model. Both methods were tested on an IEEE 14 bus system and it was shown through the results that an FDI attack that easily bypassed the bad data filter of the state estimator was successfully identified by the fixed dummy model. Second, attacks that were overlooked by the fixed dummy model were identified by the variable dummy method. In this way, the power system was protected from FDI attacks.

Prevention and detection of FDIA on power-network protection scheme using multiple support set

Usage of ICT tools for monitoring and control of power networks warrants mechanisms for robust security of supervisory control and data acquisition (SCADA) system against false data injection attack (FDIA) and detection of intruder induced manipulation of sensor information. Motivated by the aim of improving network resilience against FDIA, the present work aims at the twin objectives of providing robustness to one of the principle control actions in power networks i.e. protection relaying against FDIA and early detection of FDIA. In this context, a computationally cheap and economically viable schema based on logical analysis of data(LAD) has been proposed. The proposed scheme identifies a minimal set of secured sensors for which the network observability necessary for fault detection and classification is maintained. While preserving the observability, the mapping between sensor information and network state (healthy/faulty) allows for detecting FDIA and providing immunity to the protection scheme, irrespective of the type and extent of FDIA on the unsecured sensors.

Effective Energy Management via False Data Detection Scheme for the Interconnected Smart Energy Hub–Microgrid System under Stochastic Framework

During the last few years, attention has overwhelmingly focused on the integrated management of urban services and the demand of customers for locally-based supply. The rapid growth in developing smart measuring devices has made the underlying systems more observable and controllable. This exclusive feature has led the system designers to pursue the implementation of complex protocols to provide faster services based on data exchanges. On the other hand, the demands of consumers for locally-based supply could cause a disjunction and islanding behavior that demands to be dealt with by precise action. At first, keeping a centralization scheme was the main priority. However, the advent of distributed systems opened up new solutions. The operation of distributed systems requires the implementation of strong communication links to boost the existing infrastructure via smart control and supervision, which requires a foundation and effective investigations. Hence, necessary actions need to be taken to frustrate any disruptive penetrations into the system while simultaneously benefiting from the advantages of the proposed smart platform. This research addresses the detection of false data injection attacks (FDIA) in energy hub systems. Initially, a multi-hub system both in the presence of a microgrid (the interconnected smart energy hub-based microgrid system) and without it has been modeled for energy management in a way that allows them to cooperate toward providing energy with each other. Afterward, an FDIA is separately exerted to all three parts of the energy carrier including the thermal, water, and electric systems. In the absence of FDIA detection, the impact of FDIA is thoroughly illustrated on energy management, which considerably contributes to non-optimal operation. In the same vein, the intelligent priority selection based reinforcement learning (IPS-RL) method is proposed for FDIA detection. In order to model the uncertainty effects, the unscented transformation (UT) is applied in a stochastic framework. The results on the IEEE standard test system validate the system’s performance.

Simulation of a Fine Dust Value-Based False Data Detection System to Improve Security In WSN-Based Air Purification IoT

Fine dust refers to harmful substances floating in the air. It is divided into PM 2.5 and PM 10, and has the characteristic that the particles are small enough to be invisible to the naked eye. When fine dust enters a room, it can enter the human body through the bronchi and cause lung or respiratory diseases. To solve the health problems caused by fine dust, research and development about various air purification systems are progressing. In this paper, we introduce a Wireless Sensor Networks (WSNs)-based Internet of Things (IoT) air purification system. This WSNs-based IoT air purification system refers to a system in which an IoT air purifier and a window are automatically controlled based on fine dust values detected by sensor nodes. Therefore, because it is important to maintain the integrity of the fine dust values, SSL/TLS, an encryption protocol, is applied to this system. However, the existing SSL/TLS has a problem in which, if an attacker attempts a false data injection attack, the symmetric key itself used to encrypt and decrypt the data is stolen, so it cannot be detected. To solve this problem, in this paper we propose a Discrete Event System Specification (DEVS) model based on Data Calibration that verifies whether the fine dust values detected by sensor nodes and an IoT air purifier is within a preset error range. If the fine dust value is not within the preset error range, it is detected as false data, filtered, and not stored in the database. Because this proposed scheme verifies the integrity of the fine dust values, it not only raises the accuracy of collected sensing data, but also prevents abnormal operation of an IoT air purifier and a window in advance. Therefore, the security of the WSNs-based IoT air purification system is improved.

Detection of false data cyber-attacks for the assessment of security in smart grid using deep learning

Smart Grid uses electricity and information flows to set up a highly developed, fully automated, and distributed electricity grid system. To identify the reliability of work and availability, cyber attacks detection in the smart grids play a significant role. This paper highlights the integrity of false data cyber-attacks in the physical layers of smart grids. As the first contribution, the Proposed True Data Integrity provides an attack exposure metric through an Agent-Based Model. Next, the research focuses on the decentralization of Data Integrity Security in the system with an Agent-based approach. Finally, the productivity and efficiency of the developed modeling techniques are experimentally evaluated and compared with the existing state-of-the-art supervised deep-learning models. The obtained results of the studies have shown the improved false data detection accuracy of 98.19% through replay cyber-attacks using the Artificial Feed-forward Network. Based on the research findings, deep neural network can be used to assess cyber data in smart grids to detect malware incidents and attacks.