Mean Variance Mapping Optimization for the identification of Gaussian Mixture Model: Test case

This paper presents an application of the Mean-Variance Mapping Optimization (MVMO) algorithm to the identification of the parameters of Gaussian Mixture Model (GMM) representing variability of power system loads. The advantage of this approach is that different types of load distributions can be fairly represented as a convex combination of several normal distributions with respective means and standard deviation. The problem of obtaining various mixture components (weight, mean, and standard deviation) is formulated as a problem of identification and MVMO is used to provide an efficient solution in this paper. The performance of the proposed approach is demonstrated using two tests. Results indicate the MVMO approach is efficient to represented load models.

[1]  G. Chicco,et al.  Probability distributions of the aggregated residential load , 2006, 2006 International Conference on Probabilistic Methods Applied to Power Systems.

[2]  D. R. Limaye,et al.  Selected statistical methods for analysis of load research data. Final report , 1984 .

[3]  R. Herman,et al.  The statistical description of grouped domestic electrical load currents , 1993 .

[4]  A. Seppala,et al.  Statistical distribution of customer load profiles , 1995, Proceedings 1995 International Conference on Energy Management and Power Delivery EMPD '95.

[5]  Kaung-Hwa Chen,et al.  A multivariant exponential shared-load model , 1993 .

[6]  I. Erlich,et al.  Optimal dispatch of reactive sources in wind farms , 2011, 2011 IEEE Power and Energy Society General Meeting.

[7]  R. Jabr,et al.  Statistical Representation of Distribution System Loads Using Gaussian Mixture Model , 2010 .

[8]  Worawat Nakawiro,et al.  A novel optimization algorithm for optimal reactive power dispatch: A comparative study , 2011, 2011 4th International Conference on Electric Utility Deregulation and Restructuring and Power Technologies (DRPT).

[9]  S. Heunis,et al.  A Probabilistic Model for Residential Consumer Loads , 2002, IEEE Power Engineering Review.

[10]  Bikash Pal,et al.  Statistical Representation of Distribution System Loads Using Gaussian Mixture Model , 2010, IEEE Transactions on Power Systems.

[11]  Geoffrey J. McLachlan,et al.  Finite Mixture Models , 2019, Annual Review of Statistics and Its Application.

[12]  W. C. Beattie,et al.  Statistical electricity demand modelling from consumer billing data , 1986 .

[13]  P. Deb.  Finite Mixture Models , 2008 .

[14]  István Erlich,et al.  A Mean-Variance Optimization algorithm , 2010, IEEE Congress on Evolutionary Computation.