Scientific journal
Bulletin of Higher Educational Institutions
North Caucasus region

TECHNICAL SCIENCES


UNIV. NEWS. NORTH-CAUCAS. REG. TECHNICAL SCIENCES SERIES. 2022; 4: 20-26

 

http://dx.doi.org/10.17213/1560-3644-2022-4-20-26

 

REGRESSION MODELING AND PREDICTION OF THE MAXIMUM LOAD OF A SUBSTATION TRANSFORMER

B.B. Galabaev, A.E. Dzgoev

Galabaev Batyrbek B. – Master Student, North Caucasian Institute of Mining and Metallurgy (State Technological University), Vladikavkaz, Republic of North Ossetia-Alania, Russia, batik_333@mail.ru

Dzgoev Alan E. – Candidate of Technical Sciences, Associate Professor, Department «Information Technologies and Systems», North Caucasian Institute of Mining and Metallurgy (State Technological University), Vladikavkaz, Republic of North Ossetia-Alania, Russia, Dzgoev_Alan@mail.ru

 

 

Abstract

This article discusses the issues of the research devoted to the development of a set of candidate regression models for approximating data and forecasting the maximum load of substation transformers on a summer and winter regime day, in order to create a decision support system. Useful adequate and qualitative regression models have been developed using the least squares method (LSM). Using the criteria of mathematical statistics, we compared the values of the adequacy and quality of all developed regression candidate models and selected the most appropriate mathematical model that describes the available data on the maximum load of the transformer. Based on the data analysis and regression modeling, a decision support system was designed and a software product was developed to forecast the maximum load of a substation transformer. Predictive estimates of the maximum load will be useful to the specialists of the dispatching management of an electric distribution company in the operational control of the state of operation of electrical networks in order to ensure reliable and trouble-free operation of the entire infrastructure.

 

Keywords: set of candidate regression models, model selection, conventional linear regression, regression modeling of electric power load, data approximation, maximum load of substation transformers, decision support system

 

Full text: [in elibrary.ru]

 

References

  1. Gross G. and Galiana F.D. Short Term Load Forecasting. Proc. IEEE. 1987; 75(12):1558-1573.
  2. Automation of Dispatch Control in the Electric Power Industry / Ed. Yu.N. Rudenko and V.A. Semenova. Moscow: MPEI Publishing House; 2000. 648 p.
  3. Bann D.V., Farmer E.D. Comparative Models for Predicting Electrical Load: Per. from English. Moscow: Energoatomizdat; 1987. 200 p.
  4. Zhang D, Guan W, Yang J, Yu H, Xiao W and Yu T. Medium and Long-Term Load Forecasting Method for Group Objects Based on the Image Representation Learning. Front.2021. Energy Res. 9:739993. doi: 10.3389/fenrg.2021.739993.
  5. Chen S.T., David C.Y., Moghaddamjo A.R. Wether Sensitive Short-term Load Forecasting Using Non Fully Connected Artificial Neural Network. IEE Trans. On Power Systems. 1992; (7):1098-1105.
  6. Dash P.K., Ramakrishna G., Liew A.C., Rahman S. Fuzzy Neural Networks for Time-series Forecasting of Electric Load. IEE ProcGener. Transm. Distrib. 1995; 142(5):535-544.
  7. Dong, X., Qian, L., and Huang, L. Short-term Load forecasting in Smart Grid: a Combined CNN and K-means Clustering Approach. 2017. IEEE International Conference on Big Data & Smart Computing. New Jersey, United States: IEEE, 119–125.
  8. Anderson T. Statistical Analysis of Time Series. Moscow: 1976.
  9. Forecasting the Load of Substation Transformers. Available at: https://studbooks.net/2137251/matematika_himiya_fizika/prognozirovanie_nagruzki (accessed 23.06.2022).
  10. Sinicin F., Sokolov E. Tutorial on ML from the SHAD. Linear Models. Available at: https://ml-handbook.ru/chapters/linear_models/intro (accessed 23.06.2022).
  11. Open Machine Learning Course. Topic 4. Linear Classification and Regression Models. Available at: https://habr.com/ru/company/ods/blog/323890/ (accessed 23.06.2022).
  12. Magnus Ya.R., Katyshev P.K., Pereseckij A.A. Econometrics. Initial Course: Studies. 6th ed., reprint. and add. Moscow: Delo; 2004. 576 p. Available at: http://math.isu.ru/ru/chairs/me/files/books/magnus.pdf (accessed 23.06.2022).