This paper proposes a collaborative machine learning-based framework to detect cyber-attacks in a power system, leading to deviation in the state variable behavior. Based on the proposed architecture, three different machine learning-based methods, i.e., visualization, classification, and clustering, are employed and compared to find the best one in the FDIA detection process. To this end, pre-processing is employed in the first stage. In the second stage, the patterns of the state vectors are transferred into features. Hence, 24 statistical features, including measures of central tendency, variability, measures of shape, and position, are extracted to find various properties. Then, in the third stage, a supervised algorithm is employed to rank and find the most crucial features in FDIA. In the fourth stage, an unsupervised dimensionality reduction technique (PCA) is applied to reduce the feature space. In the fifth and last stage, visualization, classification, and clustering-based methods are developed to detect FDIA. To simulate an attack, it is assumed that an intruder decreases or increases the state vectors at different buses with various attack parameters (i.e., 0.90, 0.95, 0.96, 0.97, 0.98, 1, 1.02, 1.03, 1.04, 1.05, and 1.10). The proposed method effectiveness is assessed on the New York Independent System Operator (NYISO) data applied to the IEEE 14-bus system. The results presented in the paper from different scenarios (i.e., phase angle (θ), voltage magnitude (Vm), measurements, and multiple attacks) on a real-world dataset demonstrate that the collaborative optimized PCA-Density-based machine learning technique can detect most of the attack samples with good performance scores (i.e., recall, precision, F1) and outperforms the other investigated methods. Moreover, it is general and adaptable enough to cover the situation where either the system characteristics or the attack behavior changes.

Hardware-in-the-loop (HIL) simulation is a technique that is being used increasingly in the development and test of complex systems. Real-world testing of an intricate system in a field-like power plant can be challenging, time-consuming, expensive, and hazardous. HIL emulators allow engineers to test devices thoroughly and efficiently in a virtual environment with high reliability and minimum risk of defect. In this paper, the complete electric power system (including generator, turbine-governor, excitation system, transmission lines, transformer, external grid and related loads) is implemented in a MATLAB/Simulink environment. Different virtual instrument pages are modeled in the graphical programming language of LabVIEW which enable fast and reliable measurement functions such as data acquisition, archiving, real-time graphical display and processing. The interaction between MATLAB and LabVIEW is accomplished by generating a Pharlap ETS Targets ^* .dll file which enables the two software to exchange real-time data. Also, a real 1518-kW excitation system is considered as a test case for the introduced HIL system. This equipment is connected to LabVIEW software through a National Instrument PXI technology. Different scenarios (electrical frequency/active power change, voltage step response, etc.) are simulated in the designed power system emulator (PSE). The validity of the implemented model for the excitation system is verified by finding good matching between MATLAB and HIL simulation results.

This paper presents a high-performance hardware-in-the-loop (HIL) system aimed to assist experts in developing and testing power electronics control board and their logic with Real-Time (RT) models of both electrical and mechanical components. For demonstrating the effectiveness of this system for HIL testing, a new industrial doubly-fed induction generator (DFIG) control board is tested based on a comprehensive wind energy conversion model developed in MATLAB/Simulink hardware description language (HDL) coder and LabVIEW environment. The interaction between MATLAB/Simulink and LabVIEW is accomplished by National Instrument (NI) intellectual property (IP) integration node, which loads very high-speed integrated circuit hardware description language (VHSIC-HDL or VHDL) codes (that enable those two software exchange real-time data). LabVIEW implements a VHDL code of electrical model with fixed-point variables on an R-Series reconfigurable input/output (I/O) field-programmable gate array (FPGA) module on NI-PXIe 7858R installed on NI PXIe 1062Q chassis and the mechanical models deployed in its PXIe 8133 central processing unit (CPU). Finally, through a uniquely developed interface-board, the HIL emulator connects to an external DFIG control board. In FPGA, the model and other communicational and logging components’ step-time in each iteration is 5.0 μs. For verifying the results, a comparison is made between the proposed emulator system and Typhoon HIL602+ as a commercially-available HIL system. It is proved that there is little or no significant deviation between the two systems outputs. The proposed HIL emulator does not have the limitation of commercial HIL systems in adding custom-made new components.

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, $R^2$ ) 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.

For a number of years Power Management System (PMS) have been used to control islanded power systems. It can control system frequency and voltage as well as generated real and reactive power. The PMS would often have a load shedding facility to prevent the cascade failure of the generation system. The investigation is based on dynamics time domain simulations by DigSilent software and aims to define the main functions for the power management system (PMS) that will govern the operation of the power plant. In this paper, DigSilent Simulation Language (DSL) is used for simulation of Turbine-Governor and excitation system. Also DigSilent Program Language (DPL) is used to simulate action of PMS when it is required. Also, different dynamic contingencies related to Damavand power plant such as Trip of grid connection, Trip of One GT, Trip of load, Trip of Two GTs, Trip of Grid connection (According to governor logic, Automatic change mode acts, Solving frequency deviation by PMS) are considered. In each scenario, power plant stability is investigated and where required, PMS functions (such as load shedding and sending appropriate set points) are applied.