FEATURES OF USING REMOTE CONTROL SWITCHING DEVICES IN THE PROCESS OF FORMING ACTIVE DISTRIBUTION NETWORKS

Authors

DOI:

https://doi.org/10.20535/1813-5420.1.2020.217559

Keywords:

active distribution network, dispersed generation, electrical loads, forecasting, mode control

Abstract

Widespread introduction of sources of distributed generation in 6-10 kV networks leads to the need to use new technical means and develop an appropriate methodology for controlling regimes. At the same time, the formation of active distribution networks, as a stage of implementation of the Smart Grid concept, envisages, along with their automation, the provision of adequate information monitoring of electricity transmission and distribution processes. Only under these conditions there is a possibility of the decision of many problems of management of operating modes of distribution networks with necessary level of efficiency. Based on this, in this paper the problem of choosing the optimal configuration of the distribution network is considered as a task of operational management. To make economically justified decisions to change the topology of the distribution network, the article developed a new model for predicting the electrical load and output power of distributed generation sources. The peculiarity of this model is its adaptability and the ability to simultaneously predict the values of the relevant parameters of the mode during predetermined time intervals.

References

1. SMART GRID or smart power supply networks Available: http://www.eneca.by/ru_smartgrid0/ Accessed on 29.10.2020.

2. State of affairs with technological costs of electricity in electric networks of Ukraine Available: http://www.eneca.by/ru_smartgrid0/ Accessed on 29.10.2020.

3. Gross, G., & Galiana, F. D. “SHORT-TERM LOAD FORECASTING”. Proceedings of the IEEE, 1987, 75(12), pp. 1558-1573.

4. Y. Grichi, Y. Beauregard and T. M. Dao, "A random forest method for obsolescence forecasting," 2017 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), Singapore, 2017, pp. 1602-1606.

5. Freund, Y., and Schapire, R.E. (1996b). "A decision-theoretic generalization of on-line learning and an application to boosting", Journal of Computer and System Sciences, August 1997, pp. 119-139.

6. A. B. Nassif, "Short term power demand prediction using stochastic gradient boosting," 2016 5th International Conference on Electronic Devices, Systems and Applications (ICEDSA), 2016, pp. 1-4.

7. J. Walther, D. Spanier, N.Panten, E.Abele, ”Very short-term load forecasting on factory level – A machine learning approach”, Procedia CIRP, 2019, pp. 705-710.

8. X. Liao, N. Cao, M. Li and X. Kang, "Research on Short-Term Load Forecasting Using XGBoost Based on Similar Days," 2019 International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS), Changsha, China, 2019, pp. 675-678.

9. Ahmad, Tanveer&Zhang, Hongcai&Yan, Biao, “A review on renewable energy and electricity requirement forecasting models for smart grid and buildings”, Sustainable Citiesand Society, 2020, pp. 1-31.

10. Quinlan, J. R., “Induction of decision trees”, Machine Learning, 1986, pp. 81-106.

Downloads

Published

2020-11-26

Issue

Section

SMART GRID SYSTEM AND TECHNOLOGY