A Bayesian Approach for Parameter Estimation with Uncertainty for Dynamic Power Systems
Authors:
- Noemi PetraNPNoemi Petra
- Cosmin G. PetraCPCosmin G. Petra
- Zheng ZhangZZZheng Zhang
- Emil M. ConstantinescuECEmil M. Constantinescu
- Mihai AnitescuMAMihai Anitescu
Preprint
Abstract
We investigate two approaches, adjoint-based gradient computation and stochastic spectral methods, for parameter estimation with uncertainty in a Bayesian framework applied to power grid models. These methods are used to estimate the maximum a posteriori point of the parameters and their variance, which quantifies their uncertainty. We apply this framework to dynamic parameters, such as generator inertias, which are not estimable from steady-state models. We illustrate the performance of these approaches on a 9-bus power grid example and analyze the dependence on measurement frequency, estimation horizon, perturbation size, and measurement noise. We assess the computational efficiency, and we discuss the expected performance when these methods are applied to large systems.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Data-driven model for solar irradiation based on satellite observationsSolar Energy, 2014
- Stochastic Testing Method for Transistor-Level Uncertainty Quantification Based on Generalized Polynomial ChaosIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2013
- Reweighted minimization method for stochastic elliptic differential equationsJournal of Computational Physics, 2013
- Proper Generalized Decompositions and Separated Representations for the Numerical Solution of High Dimensional Stochastic ProblemsArchives of Computational Methods in Engineering, 2010
- Uncertainty in prior elicitations: a nonparametric approachBiometrika, 2007
- Measurement-Based Dynamic Load Models: Derivation, Comparison, and ValidationIEEE Transactions on Power Systems, 2006
- On the Parameter Estimation and Modeling of Aggregate Power System LoadsIEEE Transactions on Power Systems, 2004
- Power System Modeling for Inverse ProblemsIEEE Transactions on Circuits and Systems I: Regular Papers, 2004
- Runge-Kutta methods in optimal control and the transformed adjoint systemNumerische Mathematik, 2000
- Numerical integration using sparse gridsNumerical Algorithms, 1998