State Estimation in Electric Power Systems Leveraging Graph Neural Networks

The goal of the state estimation (SE) algorithm is to estimate complex bus voltages as state variables based on the available set of measurements in the power system. Because phasor measurement units (PMUs) are increasingly being used in transmission power systems, there is a need for a fast SE solver that can take advantage of PMU high sampling rates. This paper proposes training a graph neural network (GNN) to learn the estimates given the PMU voltage and current measurements as inputs, with the intent of obtaining fast and accurate predictions during the evaluation phase. GNN is trained using synthetic datasets, created by randomly sampling sets of measurements in the power system and labelling them with a solution obtained using a linear SE with PMUs solver. The presented results display the accuracy of GNN predictions in various test scenarios and tackle the sensitivity of the predictions to the missing input data.

State Estimation in Electric Power Systems Leveraging Graph Neural Networks

The goal of the state estimation (SE) algorithm is to estimate complex bus voltages as state variables based on the available set of measurements in the power system. Because phasor measurement units (PMUs) are increasingly being used in transmission power systems, there is a need for a fast SE solver that can take advantage of PMU high sampling rates. This paper proposes training a graph neural network (GNN) to learn the estimates given the PMU voltage and current measurements as inputs, with the intent of obtaining fast and accurate predictions during the evaluation phase. GNN is trained using synthetic datasets, created by randomly sampling sets of measurements in the power system and labelling them with a solution obtained using a linear SE with PMUs solver. The presented results display the accuracy of GNN predictions in various test scenarios and tackle the sensitivity of the predictions to the missing input data.

A Review of the Smart Grid Concept for Electrical Power System

The review this article conducts is an extensive analysis of the concept of a smart grid framework with the most sophisticated smart grid innovation and some basic information about smart grid soundness. Smart grids as a new scheme for energy and a future generation framework encourages the expansion of information and progress. The smart grid framework concord will potentially take years. In this article, the focus is on developing smart networks within the framework of electric power systems.

Model of implicit pole electric machine based on mathematical formulation of magnetic field in air gap

When modeling transient processes in electric power systems, the issue of designing reliable models of electrical machines is of great interest. The most difficult task is to design the models of synchronous and asynchronous machines. The purpose of the project is to develop mathematical models of synchronous and asynchronous machines based on a generalized model of an implicit-pole machine that considers the change of rotor speed, geometric shapes, and the type of rotor and stator windings. Methods of mathematical modeling of electromagnetic fields in the air gap based on Maxwell equations and methods of the theory of electrical circuits are applied. A system of nonlinear differential equations is considered as a mathematical model of a generalized implicit-pole machine. The key assumption made is the high magnetic permeability of the stator and rotor cores. Technical data of real electric machines have been used for verification. Mathematical models of an implicit pole synchronous machine and an asynchronous machine with a phase rotor have been developed. These models can be used to analyze transient processes in the aggregate without dividing them into electromagnetic and electromechanical ones. The novelty of the models is the fact of non-sinusoidal distribution of the magnetic field in the air gap, various types of multiphase AC windings and rejecting the principle of constant rotation frequency at the time step of the simulation. The proposed mathematical models can be used to solve design problems, to analyze the modes of electric power systems, the operation of relay protection and automation of electric power facilities, and emergency automation. In the future, the equations that consider the influence of the damper circuits and the peculiarities of the windings will be added to the developed mathematical models. The purpose of further research is to develop models of salient-pole synchronous machines and asynchronous machines with a squirrel-cage rotor.