Development of regression coefficient selection quality criterion in power consumption forecasting problems

Authors

  • Сергей Александрович Тимчук Kharkiv Petro Vasylenko National Technical University of Agriculture Engelsa 19, Kharkov, 61052, Ukraine https://orcid.org/0000-0002-8600-4234
  • Игорь Анатольевич Катюха Tavricheskiy State Agrotechnology Univercity 17 Bohdan Khmelnytsky Street, room. 1.213, Melitopol, Ukraine, 72315, Ukraine https://orcid.org/0000-0003-2757-2685

DOI:

https://doi.org/10.15587/1729-4061.2014.27664

Keywords:

power consumption forecast, fuzzy regression analysis, regression quality assessment criterion, fuzzy set

Abstract

Forecasting electricity consumption is necessary for industrial enterprises since it allows to optimize its development strategy. The initial information uncertainty problem, arising thereat is also solved using fuzzy regression analysis. Herewith, most authors estimate the quality of determining regression coefficients according to one of the criteria: maximum compatibility of data and model or minimum fuzziness of the model. These criteria are contradictory and using only one of them affects the forecasting quality.

To justify the developed quality assessment criterion of the forecast model, its unambiguous relationship with traditionally used forecast quality assessment based on the relative mean module error by modal values was mathematically proved.

To solve the problem of searching fuzzy regression coefficients using the developed criterion, a simple algorithm that implements the ideas of the method of spatial variable-pitch grid was proposed. The choice of method is caused by the fact that the possible nonlinearity of the regression forecast model requires the global optimum search method. Absolute convergence of the method is also very important.

In general, the results obtained allow to improve informativeness of system for forecasting power consumption of enterprise under initial information uncertainty.

Author Biographies

Сергей Александрович Тимчук, Kharkiv Petro Vasylenko National Technical University of Agriculture Engelsa 19, Kharkov, 61052

Ph.D., Associate Professor, Department of computer – integrated technologies

Игорь Анатольевич Катюха, Tavricheskiy State Agrotechnology Univercity 17 Bohdan Khmelnytsky Street, room. 1.213, Melitopol, Ukraine, 72315

Postgraduate student

The department of theoretical and general electrical engineering

References

  1. 1. Chang, Yun-Hsi O., Ayyub, Bilal M. (2001). Fuzzy regression methods - a comparative assessment. Fuzzy Sets and Systems, 119 (2), 187–203. http://dx.doi.org/10.1016/S0165-0114(99)00091-3

    2. Tarancev, A. A. (1997). Principy postroenija regressionnyh modelej pri ishodnyh dannyh s nechetkim opisaniem. Avtomatika i telemehanika, 215–220.

    3. Manusov, V. Z. Mogilenko, A. V. (2003). Metody ocenivanija poter' jelektrojenergii v uslovijah neopredelennosti. Jelektrichestvo, 3, 2–8.

    4. Tau Lee, H., Hua Chen, S. (2001). Fuzzy regression model with fuzzy input and output data for manpower forecasting. Fuzzy Sets and Systems, 119 (2), 205–213. http://dx.doi.org/10.1016/S0165-0114(98)00382-0

    5. Yu, J.-R., Tzeng, G.-H., Li, H.-L. (2001). General fuzzy piecewise regression analysis with automatic change-point detection. Fuzzy Sets and Systems, 119 (2), 247–257. http://dx.doi.org/10.1016/S0165-0114(98)00384-4

    6. Chen, Y.-S. (2001), Outliers detection and confidence interval modification in fuzzy regression. Fuzzy Sets and Systems, 119 (2), 259–272. http://dx.doi.org/10.1016/S0165-0114(99)00049-4

    7. Wang, H.-F., Tsaur, R.-C. (2000). Insight of a fuzzy regression model. Fuzzy Sets and Systems, 112 (3), 355–369. http://dx.doi.org/10.1016/S0165-0114(97)00375-8

    8. Celmins, A (1987). Least squares model fitting to fuzzy vector data. Fuzzy Sets and Systems, 22, 245–269. http://dx.doi.org/10.1016/0165-0114(87)90070-4

    9. Yen, K. K., Ghoshray, S., Roig, G. (1999). A linear regression model using triangular fuzzy number coefficients. Fuzzy Sets and Systems, 106, 167–177.

    10. Soliman, S. A. Abdel Rahman, H.,Mansour, M. E. El-Hawary (2000). Application of -fc fuzzy linear regression algorithm to power system voltage measurements. Electric Power Systems Research. 42 (3), 195–200. http://dx.doi.org/10.1016/s0378-7796(96)01205-9

    11. Seraya, O. V., Demin, D. A. Linear regression analysis of a small sample of fuzzy input data (2012) Journal of Automation and Information Sciences, 44 (7), 34–48. http://dx.doi.org/10.1615/jautomatinfscien.v44.i7.40

    12. Raskin, L. G., Seraja, O. V. (2008). Nechetkaja matematika. Kharkiv: Parus, 352.

    13. Buckley, J. J., Buckley, T. F. (2000). Linear and non-linear fuzzy regression: Evolutionary algorithm solutions. Fuzzy Sets and Systems, 112 (3), 381–394.

Published

2014-10-21

How to Cite

Тимчук, С. А., & Катюха, И. А. (2014). Development of regression coefficient selection quality criterion in power consumption forecasting problems. Eastern-European Journal of Enterprise Technologies, 5(8(71), 16–20. https://doi.org/10.15587/1729-4061.2014.27664

Issue

Section

Energy-saving technologies and equipment