Consumer Load Profile Determination with Entropy-Based K-Means Algorithm

Authors: Ioannis P. Panapakidis, Marios N. Moschakis

Abstract:

With the continuous increment of smart meter installations across the globe, the need for processing of the load data is evident. Clustering-based load profiling is built upon the utilization of unsupervised machine learning tools for the purpose of formulating the typical load curves or load profiles. The most commonly used algorithm in the load profiling literature is the K-means. While the algorithm has been successfully tested in a variety of applications, its drawback is the strong dependence in the initialization phase. This paper proposes a novel modified form of the K-means that addresses the aforementioned problem. Simulation results indicate the superiority of the proposed algorithm compared to the K-means.

Keywords: Clustering, load profiling, load modeling, machine learning, energy efficiency and quality.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.2643537

References:

[1] Z. Hu, X. Han, and Q. Wen, “Integrated Resource Strategic Planning and Power Demand-Side Management”, 1st ed., Springer-Verlang: Berlin, Germany, 2013, pp. 63-133.
[2] F. Rahimi and A. Ipakchi, “Overview of demand response under the smart grid and market paradigms”, In Proc. of the 2010 IEEE Innovative Smart Grid Technologies Conference, 19-21 January, Gaithersburg, Maryland, USA, pp. 1-7.
[3] International Energy Agency (IEA), Technology Roadmap Smart Grids, IEA: Paris, France, 2011.
[4] H.T. Haider, O.H. See, W. Elmenreich, “A review of residential demand response of smart grid”, Ren. Sustain. Energy Rev. vol. 59, 2016, pp. 166-178.
[5] S.S.S.R. Depuru, L. Wang and V. Devabhaktuni, “Smart meters for power grid: Challenges, issues, advantages and status”, Ren. Sust. Energy Rev., vol. 15, no. 6, pp. 2376-2742, August 2011.
[6] R. Xu and D. Wunsch, Clustering, Hoboken New Jersey, John Wiley & Sons Inc., 2006.
[7] G. Chicco, R. Napoli and F. Piglione, “Comparisons among Clustering techniques for electricity customer classification”, IEEE Trans. Power Syst. vol. 21, no.2, May 2006, pp. 933-940.
[8] G. Chicco, “Overview and performance assessment of the clustering methods for electrical load pattern”, Energy, vol. 42, 2012, pp. 68-80.
[9] X. Liu, A. Jiang, N. Xu and J. Xue, “Increment entropy as a measure of complexity for time series”, Entropy, vol. 18, no. 1, pp. 1-12.
[10] D. Steinley,“K-means clustering: A half-century synthesis”, British Journal of Mathematical and Statistical Psychology, vol. 59, 2006, pp. 1-34.
[11] G. J. Tsekouras, N. D. Hatziargyriou, and E. N. Dialynas, “Two-stage pattern recognition of load curves for classification of electricity customers”, IEEE Trans. Power Syst., vol. 22, no. 3, August 2007, pp. 1120-1128.
[12] Q. Zhao, M. Xu and P. Fränti, “Knee point detection on Bayesian information criterion”, In Proc. of the 20th IEEE International Conference on Tools with Artificial Intelligence 2008, 3-5 November 2008, Dayton, Ohio, USA, pp. 431- 438.