Searching for typical load schedule of a power facility
DOI:
https://doi.org/10.14529/power180203Keywords:
static load characteristic, daily power grid load schedule, statistical equilibrium load state, complex electric loadAbstract
One of the most important needs in planning and analyzing the operating modes of the power system is forecasting the quantities and load schedules. The paper suggests a search algorithm for the same type of load graphs based on data mining methods. The initial data is formed by the averaged half-hourly graphs of consumption of active and reactive power. The proposed algorithm is primarily aimed at preliminary processing and grouping of measurement data when solving the task of identifying static voltage load characteristics, but it is also possible to carry out research in the area of searching for typical load schedules for design and prospective calculations. The result of the data processing will be an array of labels to link the daily chart with a particular group. The proposed algorithm is based on the k-means method. The algorithm is tested on real data collected from the substation feeding the assembly plant. If the initial data is the sampling of the load curves for several years, the task of predicting the configuration of the load graph can be set. The initial data for solving this problem will be an ordered array of timestamps for the assignment of the daily load graph to a particular type.
References
C4.605 W.G. Modeling and Aggregation of Loads in Flexible Power Networks, 2014.
Pankratov A.V., Polishchuk V.I., Batseva N.L. Measurement-Based Approach for Identification of Static Load Models of Electric Power Systems. Bulletin of the South Ural State University. Ser. Power Engi-neering, 2015, vol. 15, no. 1, pp. 11–20. (in Russ.) DOI: 10.14529/power150102.
Bushueva O.A., Kuleshov A.I., Murzin A.Yu. et al. [The Experimental Studies and Determination of
the Voltage Steady-State Load Characteristics in Electric Networks with Complex Load]. State and Prospects of
the Development of Electricity and Heat Technology (XVIII Benardos Readings). Materials of the Interna-tional Scientific and Technical Conference, 2015, pp. 163–166. (in Russ.)
Berdin A.S., Bliznyuk D.I., Romanov I.B. [Estimation of Resultant Load Characteristics for Transients’ Studies]. Izvestiya NTTS Edinoy energeticheskoy sistemy [Bulletin of the United Power System], 2016, no. 1 (74), pp. 35–41. (in Russ.)
Kondrashov M.A., Smirnova A.Yu. [Application of Cluster Analysis in the Task of Identifying Static Load Characteristics]. Materials of Intellectual Energy Systems of the V International Youth Forum. National Research Tomsk Polytechnic University, 2017, pp. 79–83. (in Russ.)
Lipskiy A.M. Aronovich I.M. [Experimental Determination of Static Characteristics of Load Nodes of Electrical Systems]. Natural and Technical Sciences, 2009, no. 3 (41), pp. 410–415. (in Russ.)
Pankratov A., Kondrashov M., Paul S. Using Static Polynomial Load Models in “Rastrwin” Software Package for Power System Studies. Materials of MATEC Web of Conferences. Ser. “Smart Grids 2015”, 2015. DOI: 10.1051/matecconf/20153701039
Kondrashov M.A., Pankratov A.V. [Clustering Methods for Static Load Model Identification by the Passive Experiment Data]. Materials of the VIII International Scientific and Technical Conference “Electrici-ty in the Eyes of Youth 2017”, Samara, 2017, pp. 275–278. (in Russ.)
Drimitriev S.A., Semenenko S.I., Suvorov A.A. Complex Load Bus Static Load Characteristics Deter-mination Using Passive Experiment Method. The Seventeenth International Scientific Technical Conference “Alterna¬ting Current Electric Drive” – ACED 2018, Yekaterinburg, Russia, 26–30 March, 2018. DOI: 10.1109/ACED.2018.8341711
Tavlintsev A.S., Suvorov A.A. Statistically Equilibrium States of Load in the Problem of Static Load Characteristics Identification. Bulletin of the South Ural State University. Ser. Power Engineering, 2017, vol. 17, no. 2, pp. 23–28. (in Russ.) DOI: 10.14529/power170203.
Serria J., Arcos J.L. A Competitive Measure to Assess the Similarity Between Two Time Series. Case-Based Reasoning Research and Development, 2012, pp. 414–427. DOI: 10.1007/978-3-642-32986-9_31
Bishop C. Pattern Recognitionand Machine Learning. NewYork, Springer-Verlag . 2006.
MacQueen J. Some Methods for Classification and Analysis of Multivariate Observations. Proc. 5th Berkeley Symp. on Math. Statistics and Probability, 1967, pp. 281–297.
Laurens van der Maaten, Geoffrey Hinton. Visualizing Data Using t-SNE. Journal of Machine Learn-ing Research, 2008, no. 9, pp. 2579–2605.
