Real-time dynamic security analysis of power systems using strategic PMU measurements and decision tree classification

Mukherjee, Rituparna; De, Abhinandan

doi:10.1007/s00202-020-01118-z

Cited by 13 publications

(11 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is no limitation of the proposed GNN-based SA model for voltage SSA to apply for any other security as- sessments such as frequency, and dynamic security assessment [12], [34]. The framework is universal such that only the procedure of data generation and reliability criteria are required to be adapted.…”

Section: On a Gnn Universal Framework For The Samentioning

confidence: 99%

“…The applications of NN can be to evaluate the system security by screening the credible contingencies with loading condition and the probable contingencies as the input [11], and to estimate loadability margin concerning frequency deviation with preventive control [2]. A real-time SA to increase awareness about plausible future insecurity is applied using the Decision Tree (DT) form collection of Phase Measurement Units (PMUs) data [12]. An attempt to classify whether the power system can tolerate an (N − 1)fault during different conditions is analyzed via Support Vector Machines (SVM) with the practice of Principal Component Analysis (PCA) for dimensional reduction of feature space [13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Graph Neural Network Framework for Security Assessment Informed by Topological Measures

Dezvarei¹,

Tomsovic²,

Sun³

et al. 2023

Preprint

View full text Add to dashboard Cite

In the power system, security assessment (SA) plays a pivotal role in determining the safe operation in a normal situation and some contingencies scenarios. Electrical variables as input variables of the model are mainly considered to indicate the power system operation as secure or insecure, according to the reliability criteria for contingency scenarios. In this approach, the features are in grid format data, where the relation between features and any knowledge of network topology is absent. Moreover, the traditional and common models, such as neural networks (NN), are not applicable if the input variables are in the graph format structure. Therefore, this paper examines the security analysis in the graph neural network (GNN) framework such that the GNN model incorporates the network connection and node's neighbors' influence for the assessment. Here the input features are separated graphs representing different network conditions in electrical and structural statuses. Topological characteristics defined by network centrality measures are added in the feature vector representing the structural properties of the network. The proposed model is simulated in the IEEE 118-Bus system for the voltage static security assessment (SSA). The performance indices validate the efficiency of the GNN-based model compared to the traditional NN model denoting that the information enclosed in graph data boosts the classifier performance since the GNN model benefits the neighbors' features. Moreover, outperforming of GNN-based model is determined when robustness and sensitivity analyzes are carried out. The proposed method is not limited to a specific task and can be extended for other security assessments with different critical variables, such as dynamic analysis and frequency criteria, respectively.

show abstract

Section: On a Gnn Universal Framework For The Samentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Graph Neural Network Framework for Security Assessment Informed by Topological Measures

Dezvarei¹,

Tomsovic²,

Sun³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Our approach conceptually outperforms other state-of-the-methods in it's practicality, and ability to generate all (feasible) possible operating conditions. Typically, most state-of-the-art works consider generator outputs to be scheduled to represent conventional systems operations, often as a result of solving the optimal power flow problem that minimises generation cost [26,32,41,33,34,31,48,36]. However, as it is likely that the initial OC where a fault occurs is different from the optimal set-points, it is necessary to develop methods that explore these likely OCs [22].…”

Section: Sampling Approachesmentioning

confidence: 99%

Split-Based Sequential Sampling for Realtime Security Assessment

Bugaje¹,

Cremer²,

Štrbac³

2022

SSRN Journal

View full text Add to dashboard Cite

“…Technically, post-fault actions in the systems with PMUs belong to a critical scope of study in measurement systems. In [21], the decision tree concept is exploited to present a structure of analysis for the voltage in post-contingency conditions applying real-time information of PMUs. In addition, an adaptive forecasting process to predict the transient instability of systems through the PMU information is offered in [22,23].…”

Section: Introductionmentioning

confidence: 99%

A blockchain‐enabled secured fault allocation in smart grids based on μ PMUs and UT

Almutairi

Alrumayh

Alyami

et al. 2021

IET Renewable Power Gen

View full text Add to dashboard Cite

Improvements in the high accuracy of micro‐phasor measurement unit (μPMU) and synchrophasor unit provide the distribution network a special perspective to access full observability in the presence of renewable distribution generations (DGs). In this regard, modelling the uncertainty effects for accurate fault detection in smart grids has become a novel turning point. This research work attempts to develop a novel stochastic architecture based on unscented transform (UT), which requires a very few number of μPMUs, to communicate in a secured blockchain‐enabled structure to allocate and detect the smart grid irregularities and faults. Such a blockchain‐based technique can be beneficial for encrypting the data transmitted among the μPMUs in the smart grid consisting of a variety of distributed energy sources (DERs) and high impedance fault events, while incorporating the uncertainties associated with the load and individual installation sensors. The proposed stochastic structure benefits from voltage measurement and uses its angle in event placement that performs more efficiently than the conventional sensors based on high‐voltage and current metering. The simulation results show the great precision and effectiveness of the proposed model during various fault scenarios in smart grid.

show abstract

Real-time dynamic security analysis of power systems using strategic PMU measurements and decision tree classification

Cited by 13 publications

References 36 publications

Graph Neural Network Framework for Security Assessment Informed by Topological Measures

Graph Neural Network Framework for Security Assessment Informed by Topological Measures

Split-Based Sequential Sampling for Realtime Security Assessment

A blockchain‐enabled secured fault allocation in smart grids based on μ PMUs and UT

Contact Info

Product

Resources

About