scholarly journals Sample regenerating particle filter combined with unequal weight ensemble Kalman filter for nonlinear systems

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Xiao Li ◽  
Ai Jie Cheng ◽  
Hai Xiang Lin
Keyword(s):  
Kalman Filter ◽  
Nonlinear Systems ◽  
Particle Filter ◽  
Ensemble Kalman Filter

scholarly journals Ensemble Variational Assimilation as a Probabilistic Estimator. Part II: The fully non-linear case

2018 ◽  
Author(s):  
Mohamed Jardak ◽  
Olivier Talagrand
Keyword(s):  
Kalman Filter ◽  
Particle Filter ◽  
Objective Function ◽  
Ensemble Kalman Filter ◽  
The Other ◽  
Linear Case ◽  
Absolute Minimum ◽  
Strong Constraint ◽  
Variational Assimilation ◽  
Lorenz 96

Abstract. In Part II, the method of Ensemble Variational Assimilation (EnsVAR) is implemented in fully nonlinear conditions on the Lorenz-96 chaotic 40-parameter model. In the case of strong-constraint assimilation, it requires to be used in association with the method of Quasi-Static Variational Assimilation (QSVA). It then produces ensembles which possess as much reliability and resolution as in the linear case, and its performance is at least as good as that of Ensemble Kalman Filter and Particle Filter. On the other hand, ensembles consisting of solutions that correspond to the absolute minimum of the objective function (as identified from the minimizations without QSVA) are signif- icantly biased. In the case of weak-constraint assimilation, EnsVAR is fully successful without need to resort to QSVA.

scholarly journals Ensemble kalman filter and particle filter-based state estimation on electrical power systems

2021 ◽  
Vol 2090 (1) ◽  
pp. 012016
Author(s):  
Holger Cevallos ◽  
Gabriel Intriago ◽  
Douglas Plaza
Keyword(s):  
Kalman Filter ◽  
Power Systems ◽  
Particle Filter ◽  
State Estimation ◽  
Ensemble Kalman Filter ◽  
Electrical Power ◽  
Dynamic State ◽  
Test Case ◽  
Electrical Power Systems ◽  
Dynamic State Estimation

Abstract In this article, a referential study of the sequential importance sampling particle filter with a systematic resampling and the ensemble Kalman filter is provided to estimate the dynamic states of several synchronous machines connected to a modified 14-bus test case, when a balanced three-phase fault is applied at a bus bar near one of the generators. Both are supported by Monte Carlo simulations with practical noise and model uncertainty considerations. Such simulations were carried out in MATLAB by the Power System Toolbox, whereas the evaluation of the Particle Filter and the Ensemble Kalman Filter by script files developed inside the toolbox. The results obtained show that the particle filter has higher accuracy and more robustness to measurement and model noise than the ensemble Kalman filter, which helps support the feasibility of the method for dynamic state estimation applications.

scholarly journals A hybrid particle-ensemble Kalman filter for problems with medium nonlinearity

PLoS ONE ◽  
2021 ◽  
Vol 16 (3) ◽  
pp. e0248266
Author(s):  
Ian Grooms ◽  
Gregor Robinson
Keyword(s):  
Kalman Filter ◽  
Particle Filter ◽  
Ensemble Kalman Filter ◽  
Orthogonal Transformation ◽  
Hybrid Filter ◽  
Hybrid Particle ◽  
Particle Ensemble ◽  
Non Gaussian ◽  
Two Stages ◽  
Lorenz 96

A hybrid particle ensemble Kalman filter is developed for problems with medium non-Gaussianity, i.e. problems where the prior is very non-Gaussian but the posterior is approximately Gaussian. Such situations arise, e.g., when nonlinear dynamics produce a non-Gaussian forecast but a tight Gaussian likelihood leads to a nearly-Gaussian posterior. The hybrid filter starts by factoring the likelihood. First the particle filter assimilates the observations with one factor of the likelihood to produce an intermediate prior that is close to Gaussian, and then the ensemble Kalman filter completes the assimilation with the remaining factor. How the likelihood gets split between the two stages is determined in such a way to ensure that the particle filter avoids collapse, and particle degeneracy is broken by a mean-preserving random orthogonal transformation. The hybrid is tested in a simple two-dimensional (2D) problem and a multiscale system of ODEs motivated by the Lorenz-‘96 model. In the 2D problem it outperforms both a pure particle filter and a pure ensemble Kalman filter, and in the multiscale Lorenz-‘96 model it is shown to outperform a pure ensemble Kalman filter, provided that the ensemble size is large enough.

Sign in / Sign up

Export Citation Format

Share Document