Е-Публикации
Технически университет - София

Abstract: The paper makes an overview of the current state of short-term planning in distribution networks with connected decentralized energy sources. An approach is developed for self-adjusting of the short-term planning model for the development of distribution networks with decentralized sources, which increases the accuracy of the prognostic values. Calculations of the estimated values of the consumer load and the power production from decentralized sources are carried out using a regression model and the self-adjusting approach. It is found that the self-tuning approach gives a minimal absolute error when making a forecast for short-time day-ahead planning in electrical grids.

References

1. Strategy for Sustainable Energy Development of the Republic of Bulgaria until 2030 with a horizon until 2050. Ministry of Environment and Water (MEW), 2020.
2. Nedelcheva S.I., Electrical networks and systems with decentralized generating sources. Monograph. Sofia, ISBN 978-619-167-348-3. Publishing house of TU- Sofia, 2018.
3. Notov P.P., S.I.Nedelcheva. Electric Power. Smart Grids. Part Three. ISBN 978-619-167-119-9. Sofia, Publishing House of TU-Sofia, 2014.
4. Hasan M.K. Active-adaptive electrical networks, Monograph, ISBN 978-954-167-467-1, Sofia, Technical University of Sofia, 2022.
5. Tsvetkova P.I. Problems and influencing factors in short-term planning of the development of distribution electricity networks. ISSN 1312-3920, Proceedings of TU-Sliven, No. 4, 2022 pp.16-19.
6. Tsvetkova P.I. Short-term planning of the development of distribution electricity networks. Dissertation. Technical University of Sofia, 2023.
7. Nedeltcheva S. I., Tsvetkova P. I. Approach to short-term planning of the development of distribution electrical networks, ICEER 2023 - 10h International Conference on Energy and Environment Research: “Sustainable Development with Renewable Energy”, DOI: 10.1007/978-3-031-54394-4_2
8. Nedelcheva S.I., P.I. Tsvetkova. Algorithm for calculating parameters when choosing a strategy for short-term planning in distribution networks. ISSN 1312-3920. ISSN 1312-3920, News of TU-Sliven,, No. 3, 2023, pp. 3-8.
9. Pierrot A., Goude, Y. Short-term electricity load forecasting with generalized additive models. In Proceedings of the 16th International Conference on Intelligent System Applications to Power Systems ISAP, Hersonisos, Crete, Greece, 25–28 September 2011.
10. Nepal B., Yamaha M., Yokoe A., Yamaji A. Electricity load forecasting using clustering and ARIMA model for energy management in buildings. Jpn. Archit. Rev. 2019, 3, 62–76.
11. Tsvetkova P.I., M.S.Mladenov, A.B.Hristov. Application of the ARIMA model for short-term forecasting of electrical loads in a distribution network with decentralizedsources. ISSN 1312-3920, News of TU-Sliven,, No. 6, 2024. pp.22-29.
12. Ertugrul Ö.F., Tekin H., Tekin R. A novel regression method in forecasting short-term grid electricity load in buildings that were connected to the smart grid. Electr. Eng. 2017, 103, 717–728.
13. Li J., Deng D., Zhao J., Cai D., Hu W., Zhang M., Huang Q. A Novel Hybrid Short-Term Load Forecasting Method of Smart Grid Using MLR and LSTM Neural Network. IEEE Trans. Ind. Inform. 2021, 17, 2443–2452.
14. P. Tsvetkova. Optimum Power from Decentralized Sources in the Connecting Branches of Medium Voltage Distribution Networks, 2023 The Eighth Junior Conference on Lighting. LIGHTING 2023, DOI: 10.1109/Lighting59819.2023.10299417.
15. Tsvetkova P.I., H.S.Ilchev. Application of the multiple regression method for short-term forecasting of electrical loads ISSN 1312-3920, News of TU-Sliven,, No. 4, 2023. pp. 3-8.
16. Tsvetkova P.I., H.S.Ilchev. Application of artificial neural network for short-term forecasting of electrical loads. ISSN 1312-3920, News of TU-Sliven,, No. 4, 2023. pp.9-12.
17. Hassan M. K. Variant Study of the Electrical Energy Supply to an Autonomous Consumer by Means of Wind Power Plants. 2024 9th International Conference on Energy Efficiency and Agricultural Engineering (EE&AE). 10.1109/EEAE60309.2024.10600619
18. Yahya М.А., S.P.Hadi, L.M.Putranto. Short-Term Electric Load Forecasting Using Recurrent Neural Network. 2018 4th International Conference on Science and Technology (ICST). Yogyakarta, Indonesia, 07-08 August 2018.
19. Wang X., Y. Chen, J.Jin, B.Zhang. Fuzzy-clustering and fuzzy network based interpretable fuzzy model for prediction. Scientific Reports, volume 12, Article number: 16279, 2022.
20. Nedelcheva S.I., P.I. Tsvetkova. Adaptive approach for short-term forecasting of the capacities of consumers and decentralized producers in distribution networks. ISSN 1312-3920, News of TU-Sliven,, No. 4, 2023, pp. 13-22.
21. Wood S., Goude Y., Shaw S., Generalized additive models for large data sets. J. R. Stat. Soc. Appl. Stat. 2015, 64, 139–155.
22. Krstonijević S. Adaptive Load Forecasting Methodology Based on Generalized Additive Model with Automatic Variable Selection. Sensors 2022, 22(19).
23. Ilchev H. S. Influence of the neutral grounding mode on the reliability of actively adaptive electric grids, ICEER 2023 - 10h International Conference on Energy and Environment Research: “Sustainable Development with Renewable Energy”, DOI: 10.1007/978-3-031-54394-4_3.
24. Raykov K. V. Improvement of energy efficiency in distribution networks. The International Journal of Engineering and Science (IJES), vol. 11, issue 11, pp. 32-34, 2022, India, DOI 10.9790/1813-11113234.
25. Savov N. V. Options for Power Supplying an Object by Medium or High Voltage. 2024 9th Junior Conference on Lighting, Lighting 2024, DOI: 10.1109/Lighting62260.2024.10590671.
26. Hassan M., Ramadan F. Study of the distribution of scattered magnetic conductivities in a "Sh"-shaped electromagnet. X-th jubilee national scientific conference with international participation "Active-adaptive electric networks'24". Burgas. News of TU-Sliven No 5, 2024, Bulgaria, ISSN 1312-3920.

Issue