1 code implementation • 20 Apr 2024 • Ignasi Ventura Nadal, Jochen Stiasny, Spyros Chatzivasileiadis
This paper introduces the first natural step to remove the barriers for using PINNs in time-domain simulations: it proposes the first method to integrate PINNs in conventional numerical solvers.
no code implementations • 12 Feb 2024 • Petros Ellinas, Rahul Nellikath, Ignasi Ventura, Jochen Stiasny, Spyros Chatzivasileiadis
Finally, for the first time, we tackle the problem of bounding an NN function without a priori knowledge of the output domain.
no code implementations • 10 Jan 2024 • Jochen Stiasny, Spyros Chatzivasileiadis
We find that this error estimate highly correlates with the NN's prediction error and that increasing the order of the IRK method improves this estimate.
no code implementations • 17 Mar 2023 • Jochen Stiasny, Baosen Zhang, Spyros Chatzivasileiadis
To accelerate these simulations, we propose a simulator -- PINNSim -- that allows to take significantly larger time steps.
no code implementations • 15 Mar 2023 • Jochen Stiasny, Spyros Chatzivasileiadis
Comparing the prediction of PINNs to the solution of conventional solvers, we find that PINNs can be 10 to 1000 times faster than conventional solvers.
no code implementations • 22 Dec 2022 • Simon Stock, Jochen Stiasny, Davood Babazadeh, Christian Becker, Spyros Chatzivasileiadis
Bayesian Physics-Informed Neural Networks (BPINNs) combine the advantages of Physics-Informed Neural Networks (PINNs), being robust to noise and missing data, with Bayesian modeling, delivering a confidence measure for their output.
no code implementations • 13 Sep 2022 • Robert I. Hamilton, Jochen Stiasny, Tabia Ahmad, Samuel Chevalier, Rahul Nellikkath, Ilgiz Murzakhanov, Spyros Chatzivasileiadis, Panagiotis N. Papadopoulos
To do so, we demonstrate that the Power Transfer Distribution Factors (PTDF) -- a physics-based linear sensitivity index -- can be derived from the SHAP values.
1 code implementation • 14 Mar 2022 • Jochen Stiasny, Samuel Chevalier, Rahul Nellikkath, Brynjar Sævarsson, Spyros Chatzivasileiadis
Deep decarbonization of the energy sector will require massive penetration of stochastic renewable energy resources and an enormous amount of grid asset coordination; this represents a challenging paradigm for the power system operators who are tasked with maintaining grid stability and security in the face of such changes.
no code implementations • 30 Jun 2021 • Jochen Stiasny, Samuel Chevalier, Spyros Chatzivasileiadis
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.
1 code implementation • 25 Jun 2021 • Jochen Stiasny, Georgios S. Misyris, Spyros Chatzivasileiadis
Physics-informed neural networks are different: they incorporate the power system differential algebraic equations directly into the neural network training and drastically reduce the need for training data.
no code implementations • 4 Jun 2021 • Samuel Chevalier, Jochen Stiasny, Spyros Chatzivasileiadis
In the second approach, we model the Newton solver at the heart of an implicit Runge-Kutta integrator as a contracting map iteratively seeking a fixed point on a time domain trajectory.
1 code implementation • 31 Mar 2021 • Georgios S. Misyris, Jochen Stiasny, Spyros Chatzivasileiadis
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.
1 code implementation • 8 Apr 2020 • Jochen Stiasny, George S. Misyris, Spyros Chatzivasileiadis
Varying power-infeed from converter-based generation units introduces great uncertainty on system parameters such as inertia and damping.