IEEE Systems Journal · 2019 · 25 citations · 31 references
EngineeringSystems EngineeringStochastic ModelingTime Series AnalysisUncertainty QuantificationMaximum Likelihood EstimationMicrogridsPower Grid AnalysisPower SystemsRobust StatisticsState EstimationInfluence FunctionInfluence Function AnalysisMean Squared ErrorNoise-robust EstimationRobust EstimationRobust State Estimation
In this paper, we propose an optimal robust state estimator using maximum likelihood optimization with the t-distribution noise model. In robust statistics literature, the t-distribution is used to model Gaussian and non-Gaussian statistics. The influence function, an analytical tool in robust statistics, is employed to obtain the solution to the resulting maximum likelihood estimation optimization problem, so that the proposed estimator can be implemented within the framework of traditional robust estimators. Numerical results obtained from simulations of the IEEE 14-bus system, IEEE 118-bus system, and experiment on a microgrid demonstrated the effectiveness and robustness of the proposed estimator. The proposed estimator could suppress the influence of outliers with smaller average mean-squared errors (AMSE) than the traditional robust estimators, such as quadratic-linear, squareroot, Schweppe-Huber generalized-M, multiple-segment, and least absolute value estimators. A new approximate AMSE formula is also derived for the proposed estimator to predict and evaluate its precision.
31
Robust Statistics: The Approach Based on Influence Functions
David Ruppert, Frank R. Hampel, Elvezio Ronchetti et al. · Technometrics · 1987 · 3.8K citations
J. Freeman, Vic Barnett, Toby Lewis · Journal of the Operational Research Society · 1995 · 727 citations
Computing, Data Science, Mathematics +12