Biblio

This paper proposes a machine-learning-based advanced online dynamic security assessment (DSA) method, which provides a detailed evaluation of the system stability after a disturbance by predicting impending loss of synchronism (LOS) of generators. Voltage angles at generator buses are used as the features of the different random forest (RF) classifiers which are trained to consecutively predict LOS of the generators as a contingency proceeds and updated measurements become available. A wide range of contingencies for various topologies and operating conditions of the IEEE 118-bus system has been studied in offline analysis using the GE positive sequence load flow analysis (PSLF) software to create a comprehensive dataset for training and testing the RF models. The performances of the trained models are evaluated in the presence of measurement errors using various metrics. The results reveal that the trained models are accurate, fast, and robust to measurement errors.

Large-scale blackouts that have occurred in the past few decades have necessitated the need to do extensive research in the field of grid security assessment. With the aid of synchrophasor technology, which uses phasor measurement unit (PMU) data, dynamic security assessment (DSA) can be performed online. However, existing applications of DSA are challenged by variability in system conditions and unaccounted for measurement errors. To overcome these challenges, this research develops a DSA scheme to provide security prediction in real-time for load profiles of different seasons in presence of realistic errors in the PMU measurements. The major contributions of this paper are: (1) develop a DSA scheme based on PMU data, (2) consider seasonal load profiles, (3) account for varying penetrations of renewable generation, and (4) compare the accuracy of different machine learning (ML) algorithms for DSA with and without erroneous measurements. The performance of this approach is tested on the IEEE-118 bus system. Comparative analysis of the accuracies of the ML algorithms under different operating scenarios highlights the importance of considering realistic errors and variability in system conditions while creating a DSA scheme.

This paper presents a methodology for utilizing Phasor Measurement units (PMUs) for procuring real time synchronized measurements for assessing the security of the power system dynamically. The concept of wide-area dynamic security assessment considers transient instability in the proposed methodology. Intelligent framework based approach for online dynamic security assessment has been suggested wherein the database consisting of critical features associated with the system is generated for a wide range of contingencies, which is utilized to build the data mining model. This data mining model along with the synchronized phasor measurements is expected to assist the system operator in assessing the security of the system pertaining to a particular contingency, thereby also creating possibility of incorporating control and preventive measures in order to avoid any unforeseen instability in the system. The proposed technique has been implemented on IEEE 39 bus system for accurately indicating the security of the system and is found to be quite robust in the case of noise in the measurement data obtained from the PMUs.

Online Dynamic Security Assessment (DSA) is a dynamical system widely used for assessing and analyzing an electrical power system. The outcomes of DSA are used in many aspects of the operation of power system, from monitoring the system to determining remedial action schemes (e.g. the amount of generators to be shed at the event of a fault). Measurement from supervisory control and data acquisition (SCADA) and state estimation (SE) results are the inputs for online-DSA, however, the SE error, caused by sudden change in power flow or low convergence rate, could be unnoticed and skew the outcome. Therefore, generator shedding scheme cannot achieve optimum but must have some margin because we don't know how SE error caused by these problems will impact power system stability control. As a method for solving the problem, we developed SE error detection system (EDS), which is enabled by detecting the SE error that will impact power system transient stability. The method is comparing a threshold value and an index calculated by the difference between SE results and PMU observation data, using the distance from the fault point and the power flow value. Using the index, the reliability of the SE results can be verified. As a result, online-DSA can use the SE results while avoiding the bad SE results, assuring the outcome of the DSA assessment and analysis, such as the amount of generator shedding in order to prevent the power system's instability.