Physics-Informed Neural Networks for Non-linear System Identification for Power System Dynamics

Stiasny, Jochen; Misyris, George S.; Chatzivasileiadis, Spyros

doi:10.1109/powertech46648.2021.9495063

Cited by 32 publications

(34 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we propose a novel data-driven algorithm to solve the parameter estimation problem based on the SINDy algorithm [20], which leverages the knowledge of the differential equations describing the physical system to identify the system parameters. We also briefly describe the PINN approach to estimate the system parameters [16], which also similarly uses the knowledge of the system model.…”

Section: Physics-informed Machine Learning Techniques For Power Grid ...mentioning

confidence: 99%

“…The focus of this work is mainly on estimating the power system parameters based on the data from the transient dynamics [12][13][14][15][16], i.e., the system identification problem. This problem has been primarily addressed through the application of the Kalman filter approach and its variants [17].…”

Section: Introductionmentioning

confidence: 99%

“…However, dynamic state/parameter estimation methods using KF suffer from scalability issue for large-scale systems. The authors of a recent work [16] proposed physics-informed neural networks (PINNs) approach for this problem. Since it is based on NNs, it is capable of handling strong nonlinearity.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Application of Physics-Informed Machine Learning Techniques for Power Grid Parameter Estimation

2022

View full text Add to dashboard Cite

Power grid parameter estimation involves the estimation of unknown parameters, such as the inertia and damping coefficients, from the observed dynamics. In this work, we present physics-informed machine learning algorithms for the power system parameter estimation problem. First, we propose a novel algorithm to solve the parameter estimation based on the Sparse Identification of Nonlinear Dynamics (SINDy) approach, which uses sparse regression to infer the parameters that best describe the observed data. We then compare its performance against another benchmark algorithm, namely, the physics-informed neural networks (PINN) approach applied to parameter estimation. We perform extensive simulations on IEEE bus systems to examine the performance of the aforementioned algorithms. Our results show that the SINDy algorithm outperforms the PINN algorithm in estimating the power grid parameters over a wide range of system parameters (including high and low inertia systems) and power grid architectures. Particularly, in case of the slow dynamics system, the proposed SINDy algorithms outperforms the PINN algorithm, which struggles to accurately determine the parameters. Moreover, it is extremely efficient computationally and so takes significantly less time than the PINN algorithm, thus making it suitable for real-time parameter estimation. Furthermore, we present an extension of the SINDy algorithm to a scenario where the operator does not have the exact knowledge of the underlying system model. We also present a decentralised implementation of the SINDy algorithm which only requires limited information exchange between the neighbouring nodes of a power grid.

show abstract

Section: Physics-informed Machine Learning Techniques For Power Grid ...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of Physics-Informed Machine Learning Techniques for Power Grid Parameter Estimation

2022

View full text Add to dashboard Cite

show abstract

“…1. Physics-informed neural network architecture (adapted from [18]), consisting of a dense neural network (NN), followed by applying automatic differentiation (AD) to the differential states x. The calculation of the losses is based on data (L i x , L i y ) and on the governing equations (L i f , L i g ).…”

Section: Nn Admentioning

confidence: 99%

Capturing Power System Dynamics by Physics-Informed Neural Networks and Optimization

Misyris¹,

Stiasny²,

Chatzivasileiadis³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

This paper proposes a tractable framework to determine key characteristics of non-linear dynamic systems by converting physics-informed neural networks to a mixed integer linear program. Our focus is on power system applications. Traditional methods in power systems require the use of a large number of simulations and other heuristics to determine parameters such as the critical clearing time, i.e. the maximum allowable time within which a disturbance must be cleared before the system moves to instability. The work proposed in this paper uses physics-informed neural networks to capture the power system dynamic behavior and, through an exact transformation, converts them to a tractable optimization problem which can be used to determine critical system indices. By converting neural networks to mixed integer linear programs, our framework also allows to adjust the conservativeness of the neural network output with respect to the existing stability boundaries. We demonstrate the performance of our methods on the non-linear dynamics of converter-based generation in response to voltage disturbances.

show abstract

“…Physics-informed neural networks have been first introduced in power systems in our previous work [18], and, since then, have extended in applications related to system identification [19], the transient response of interconnected systems [20], and DC optimal power flow [21]; along the same lines, sensitivity-informed NNs have been recently introduced for AC power flow optimization [22] and physics-informed graphical NNs for parameter estimation [23]. All of these works, however, have utilised a continuous formulation of the problem's underlying physics and have thus required simulated training data.…”

Section: Introductionmentioning

confidence: 99%

Learning without Data: Physics-Informed Neural Networks for Fast Time-Domain Simulation

Stiasny¹,

Chevalier²,

Chatzivasileiadis³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

In order to drastically reduce the heavy computational burden associated with time-domain simulations, this paper introduces a Physics-Informed Neural Network (PINN) to directly learn the solutions of power system dynamics. In contrast to the limitations of classical model order reduction approaches, commonly used to accelerate time-domain simulations, PINNs can universally approximate any continuous function with an arbitrary degree of accuracy. One of the novelties of this paper is that we avoid the need for any training data. We achieve this by incorporating the governing differential equations and an implicit Runge-Kutta (RK) integration scheme directly into the training process of the PINN; through this approach, PINNs can predict the trajectory of a dynamical power system at any discrete time step. The resulting Runge-Kutta-based physics-informed neural networks (RK-PINNs) can yield up to 100 times faster evaluations of the dynamics compared to standard time-domain simulations. We demonstrate the methodology on a single-machine infinite bus system governed by the swing equation. We show that RK-PINNs can accurately and quickly predict the solution trajectories.

show abstract

Physics-Informed Neural Networks for Non-linear System Identification for Power System Dynamics

Cited by 32 publications

References 11 publications

Application of Physics-Informed Machine Learning Techniques for Power Grid Parameter Estimation

Application of Physics-Informed Machine Learning Techniques for Power Grid Parameter Estimation

Capturing Power System Dynamics by Physics-Informed Neural Networks and Optimization

Learning without Data: Physics-Informed Neural Networks for Fast Time-Domain Simulation

Contact Info

Product

Resources

About